<![CDATA[Azad Academy]]>https://azadacademy.substack.comhttps://substackcdn.com/image/fetch/w_256,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fc3bcab9d-a13a-4b1e-901e-b8106cf2cc03_568x568.pngAzad Academyhttps://azadacademy.substack.comSubstackMon, 25 Nov 2024 17:06:15 GMT<![CDATA[Why Convolve? : Understanding Convolution and Feature Extraction in Deep Networks]]>https://azadacademy.substack.com/p/why-convolve-understanding-convolutionhttps://azadacademy.substack.com/p/why-convolve-understanding-convolutionSun, 05 Feb 2023 05:24:37 GMT
Figure 1: 1D/2D Convolutions and an Interactive Visualization Tool (Source: Author)

It is a common practice nowadays to construct deep neural networks with a set of convolution layers. However, it was not always like this, earlier neural networks and other machine learning frameworks didn’t employ convolutions. Feature extraction and learning were two separate fields of study until recently. This is why it is important to understand how Convolution works and why it took such an important place in deep learning architectures. In this article we shall explore the Convolution thoroughly and you would be able to understand the concept more deeply with an interactive tool.

Read more

]]><![CDATA[Evaluation Methods for Machine Learning Classifiers]]>https://azadacademy.substack.com/p/evaluation-of-machine-learning-classifiershttps://azadacademy.substack.com/p/evaluation-of-machine-learning-classifiersMon, 16 Jan 2023 06:42:17 GMT
Figure 1: A depiction of Results from a Bias-Variance Analysis (Source: Author)

In the previous articles, we have discussed various Machine Learning methods for classification tasks. We have also used terms like Regularization, Overfitting and Underfitting repeatedly. In this article, we shall go through these terms in detail and show how you can circumvent such problems. Furthermore, we shall also discuss various metrics for measuring the performance of a classifier.

Read more

]]>
<![CDATA[ML Basics (Part-4): Decision Trees]]>https://azadacademy.substack.com/p/ml-basics-part-4-decision-treeshttps://azadacademy.substack.com/p/ml-basics-part-4-decision-treesWed, 04 Jan 2023 09:11:47 GMT
Figure 1: Decision Tree Classifiers (Source: Author)

In the previous articles, we have explored the concepts of Regression, Support Vector Machines, and Artificial Neural Networks. In this article, we shall go through another Machine Learning concept called, Decision Trees. You can check-out the other methods from the aforementioned links.

Read more

]]>
<![CDATA[ML Basics (Part-3): Artificial Neural Networks]]>https://azadacademy.substack.com/p/ml-basics-part-3-artificial-neuralhttps://azadacademy.substack.com/p/ml-basics-part-3-artificial-neuralSun, 25 Dec 2022 09:00:56 GMT
Figure 1: Artificial Neural Network Interactive Tool for Visualization and Learning

In the previous posts, we have discussed Regression and Support Vector Machines (SVM) as two important methods in Machine Learning. SVM has some similarity to a Regression Analysis, However, there is a method that is a direct descendent of a Logistic Regression. It is called ‘Artificial Neural Network (ANN)’. We shall build an ANN from scratch in this article, and you would be able to understand the concept with an interactive tool.

Read more

]]>
<![CDATA[ML Basics (Part-2): Support Vector Machines]]>https://azadacademy.substack.com/p/ml-basics-part-2-support-vector-machineshttps://azadacademy.substack.com/p/ml-basics-part-2-support-vector-machinesMon, 12 Dec 2022 11:13:05 GMT
Figure 1: Depiction of a Support Vector Machine Model in an example of Soldiers at War (Source: Author)

In the previous post we learned about the Regression methods. In this article we shall go through a similar but slightly advanced machine learning method called “Support Vector Machine (SVM)”. Unless you are already familiar, it is advised that you check out the previous post first before reading this article.

Read more

]]>
<![CDATA[ML Basics (Part-1): REGRESSION — A Gateway Method to Machine Learning]]>https://azadacademy.substack.com/p/ml-basics-part-1-regression-a-gatewayhttps://azadacademy.substack.com/p/ml-basics-part-1-regression-a-gatewaySun, 04 Dec 2022 06:33:03 GMT
Figure 1: Examples of Linear, Non-Linear and Logistic Regression (Source: Author)

Preface:

There has been growing interest in the introductory posts on the elementary topics in Machine Learning. So, I am writing on such topics in the coming posts starting from this one. This article is mostly self-contained however, it requires basic understanding of linear algebra, and calculus.

Read more

]]>
<![CDATA[Matters of Attention: What is Attention and How to Compute Attention in a Transformer Model]]>https://azadacademy.substack.com/p/matters-of-attention-what-is-attentionhttps://azadacademy.substack.com/p/matters-of-attention-what-is-attentionSun, 20 Nov 2022 05:25:03 GMT
Figure 1: Attention in a Transformer Model (Source: Author)

In this article, you will learn about Attention, its computation and role in a transformer network.  You will also learn about vector embedding, position embedding and attention implementation in a text transformer. This will make use of concepts, “Transformers” and “Autoencoders”, so, if you would like to learn more about these topics then feel free to check out my earlier posts.

Read more

]]>
<![CDATA[How to Improve Performance of a Diffusion Model by an Ensemble of Expert Models]]>https://azadacademy.substack.com/p/how-to-improve-performance-of-a-diffusionhttps://azadacademy.substack.com/p/how-to-improve-performance-of-a-diffusionSat, 12 Nov 2022 07:35:42 GMTIn this article we shall go through a recent development in the Diffusion Model domain called eDiff-I [1]. It is an ensemble of Diffusion Models which seems to have outperformed all the other state-of-the-art (e.g., DALL-E2 and Stable Diffusion Model). This article will build upon earlier concepts (e.g., Diffusion Models and Stable Diffusion Models). Feel free to checkout my earlier posts on these topics.

Figure 1: Binary Tree Diagram Depicting an Ensemble of Diffusion Models being trained at Various Noise Levels (Source: Author)

Read more

]]>
<![CDATA[Beyond Diffusion: What is Personalized Image Generation and How Can You Customize Image Synthesis?]]>https://azadacademy.substack.com/p/beyond-diffusion-what-is-personalizedhttps://azadacademy.substack.com/p/beyond-diffusion-what-is-personalizedMon, 17 Oct 2022 08:53:36 GMT
Figure 1: Personalized Diffusion In Action (Source: Author)

In this article you will learn about customization and personalization of diffusion model based image generation. More specifically, you will learn about the Textual-Inversion and Dream-Booth. This article will build upon the concepts of Autoencoders, Stable Diffusion Models (SD) and Transformers. So, if you would like to know more about those concepts, feel free to checkout my earlier posts on these topics.

Read more

]]>
<![CDATA[What is a Stable Diffusion Model and Why is it a Step Forward for Image Generation? ]]>https://azadacademy.substack.com/p/what-is-a-stable-diffusion-modelhttps://azadacademy.substack.com/p/what-is-a-stable-diffusion-modelMon, 03 Oct 2022 10:59:58 GMT
Figure 1: Latent Diffusion Model (Base Diagram:[3], Concept-Map Overlay: Author)

In this article you will learn about a recent advancement in Image Generation domain. More specifically, you will learn about the Latent Diffusion Models (LDM) and their applications. This article will build upon the concepts of GANs, Diffusion Models and Transformers. So, if you would like to dig deeper into those concepts, feel free to checkout my earlier posts on these topics.

Read more

]]>
<![CDATA[What Are Vision Transformers And How Are They Important For General Purpose Learning? ]]>https://azadacademy.substack.com/p/what-are-vision-transformers-andhttps://azadacademy.substack.com/p/what-are-vision-transformers-andSat, 20 Aug 2022 03:45:00 GMT
Figure 1: Vision Transformers in Action (Source: Author)

There has been a significant advancement in the field of AI in the past several years. Generative models have been the most successful in the vision domain however, they are built for highly specialized tasks. These specialized learning models require reconstruction or retraining whenever the task is changed. Therefore, the interest in General purpose learning models is increasing. One of such type of models is called Transformers. In this article, we briefly discuss:

  • What is a Transformer?

  • What is a Vision Transformer (ViT)?

  • What are the various applications of ViTs?

  • How can ViTs be used for general purpose learning?

Read more

]]>
<![CDATA[Diffusion Models Made Easy ]]>https://azadacademy.substack.com/p/diffusion-models-made-easyhttps://azadacademy.substack.com/p/diffusion-models-made-easyWed, 03 Aug 2022 03:33:00 GMT
Figure 1: Process of Denoising Diffusion Probabilistic Model (Source: Author)

Read more

]]>
<![CDATA[Draw the Desire: Bringing the sketches to life using Deep Learning ]]>https://azadacademy.substack.com/p/draw-the-desire-bringing-the-sketcheshttps://azadacademy.substack.com/p/draw-the-desire-bringing-the-sketchesSat, 30 Jul 2022 03:17:00 GMTIn this article, you will learn about conditional GAN (Generative Adversarial Network) and will be able to build one from scratch. After that you will be able to apply the cGAN model on a fashion products dataset for converting sketches of products to color images. If you would like to understand what are GANs [1] you can check out our previous tutorials on Latent Spaces.

Figure 1: An example output of the GAN network trained on Fashion Products

Read more

]]>
<![CDATA[TerrificEye: An Edge Computing System For Traffic Analytics From Videos ]]>https://azadacademy.substack.com/p/terrificeye-an-edge-computing-systemhttps://azadacademy.substack.com/p/terrificeye-an-edge-computing-systemWed, 20 Jul 2022 03:05:00 GMT
Figure 1: TerrificEye System (Source: Author)

Read more

]]>
<![CDATA[Why Is Cross Entropy Equal to KL-Divergence?]]>https://azadacademy.substack.com/p/why-is-cross-entropy-equal-to-klhttps://azadacademy.substack.com/p/why-is-cross-entropy-equal-to-klFri, 15 Jul 2022 02:50:00 GMT
Figure 1: Two probability distributions sampled from normal distribution (Image by author)

It is a common practice to use cross-entropy in the loss function while constructing a Generative Adversarial Network [1] even though original concept suggests the use of KL-divergence. This creates confusion often for the person new to the field. In this article we go through the concepts of entropy, cross-entropy and Kullback-Leibler Divergence [2] and see how they can be approximated to be equal.

Read more

]]>
<![CDATA[A Practical Introduction to Deep Convolutional Generative Adversarial Network (DCGAN)]]>https://azadacademy.substack.com/p/a-practical-introduction-to-deephttps://azadacademy.substack.com/p/a-practical-introduction-to-deepThu, 30 Jun 2022 01:58:00 GMTIn the previous tutorial we learned about variational autoencoders and their implementation in TensorFlow. In this tutorial, we shall explore another deep learning architecture called Generative Adversarial Network (GAN).

Figure 1: An example output of a DCGAN trained on Bicycles Dataset

Read more

]]>
<![CDATA[What are Variational Autoencoders?]]>https://azadacademy.substack.com/p/what-are-variational-autoencodershttps://azadacademy.substack.com/p/what-are-variational-autoencodersTue, 31 May 2022 07:37:20 GMT
Figure 1: An example output of a Variational autoencoder

In the previous tutorial (https://medium.com/mlearning-ai/latent-space-representation-a-hands-on-tutorial-on-autoencoders-in-tensorflow-57735a1c0f3f) we learned about latent spaces, autoencoders and their implementation in TensorFlow. In this tutorial, we shall extend the concept of autoencoders and look at one of the special cases of autoencoders called variational autoencoders.

Read more

]]>
<![CDATA[LATENT SPACE REPRESENTATION ]]>https://azadacademy.substack.com/p/latent-space-representationhttps://azadacademy.substack.com/p/latent-space-representationThu, 19 May 2022 09:48:51 GMTThis is a part-1 of the series of tutorials that I am writing on unsupervised/self-supervised learning using deep neural networks. This would cover the following topics:

·       Autoencoders

·       Variational Autoencoders

·       Generative Adversarial Networks

In this tutorial, the focus would be on latent space implementation using autoencoder architecture and its visualization using t-SNE embedding. Before we delve into code, lets define some important concepts which we will encounter throughout the tutorial.

Read more

]]>
This XML file does not appear to have any style information associated with it. The document tree is shown below.
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:itunes="http://www.itunes.com/dtds/podcast-1.0.dtd" xmlns:googleplay="http://www.google.com/schemas/play-podcasts/1.0" version="2.0">
<channel>
<title>
<![CDATA[ Azad Academy ]]>
</title>
<description>
<![CDATA[ A place for learning in the fields of Deep Learning, Machine Learning, Computer Vision, and Artificial Intelligence. Specially useful for Students, ML Engineers, Data Scientists and AI Artists. ]]>
</description>
<link>https://azadacademy.substack.com</link>
<image>
<url>https://substackcdn.com/image/fetch/w_256,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fc3bcab9d-a13a-4b1e-901e-b8106cf2cc03_568x568.png</url>
<title>Azad Academy</title>
<link>https://azadacademy.substack.com</link>
</image>
<generator>Substack</generator>
<lastBuildDate>Mon, 25 Nov 2024 17:06:15 GMT</lastBuildDate>
<atom:link href="https://azadacademy.substack.com/feed" rel="self" type="application/rss+xml"/>
<copyright>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</copyright>
<language>
<![CDATA[ en ]]>
</language>
<webMaster>
<![CDATA[ azadacademy@substack.com ]]>
</webMaster>
<itunes:owner>
<itunes:email>
<![CDATA[ azadacademy@substack.com ]]>
</itunes:email>
<itunes:name>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</itunes:name>
</itunes:owner>
<itunes:author>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</itunes:author>
<googleplay:owner>
<![CDATA[ azadacademy@substack.com ]]>
</googleplay:owner>
<googleplay:email>
<![CDATA[ azadacademy@substack.com ]]>
</googleplay:email>
<googleplay:author>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</googleplay:author>
<item>
<title>
<![CDATA[ Why Convolve? : Understanding Convolution and Feature Extraction in Deep Networks ]]>
</title>
<description>
<![CDATA[ An Explanation of 1D/2D Convolution, its Role in Feature Learning, and a Visualization Tool ]]>
</description>
<link>https://azadacademy.substack.com/p/why-convolve-understanding-convolution</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/why-convolve-understanding-convolution</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Sun, 05 Feb 2023 05:24:37 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5f0bb626-e454-4cf8-94c5-51dd5b110f46_1920x1080.png" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-imag" target="_blank" href="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5f0bb626-e454-4cf8-94c5-51dd5b110f46_1920x1080.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5f0bb626-e454-4cf8-94c5-51dd5b110f46_1920x1080.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5f0bb626-e454-4cf8-94c5-51dd5b110f46_1920x1080.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5f0bb626-e454-4cf8-94c5-51dd5b110f46_1920x1080.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5f0bb626-e454-4cf8-94c5-51dd5b110f46_1920x1080.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5f0bb626-e454-4cf8-94c5-51dd5b110f46_1920x1080.png" width="1456" height="819" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/5f0bb626-e454-4cf8-94c5-51dd5b110f46_1920x1080.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:819,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:1017808,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5f0bb626-e454-4cf8-94c5-51dd5b110f46_1920x1080.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5f0bb626-e454-4cf8-94c5-51dd5b110f46_1920x1080.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5f0bb626-e454-4cf8-94c5-51dd5b110f46_1920x1080.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F5f0bb626-e454-4cf8-94c5-51dd5b110f46_1920x1080.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></div></div></a><figcaption class="image-caption">Figure 1: 1D/2D Convolutions and an Interactive Visualization Tool (Source: Author)</figcaption></figure></div><p></p><p>It is a common practice nowadays to construct deep neural networks with a set of convolution layers. However, it was not always like this, earlier neural networks and other machine learning frameworks didn&#8217;t employ convolutions. Feature extraction and learning were two separate fields of study until recently. This is why it is important to understand how Convolution works and why it took such an important place in deep learning architectures. In this article we shall explore the Convolution thoroughly and you would be able to understand the concept more deeply with an interactive tool.</p><p></p> <p> <a href="https://azadacademy.substack.com/p/why-convolve-understanding-convolution"> Read more </a> </p> ]]>
</content:encoded>
</item>
<item>
<title>
<![CDATA[ Evaluation Methods for Machine Learning Classifiers ]]>
</title>
<description>
<![CDATA[ Explanation of Bias-Variance Analysis, Regularization, Performance Metrics, and an Implementation of Harmonic Classifier ]]>
</description>
<link>https://azadacademy.substack.com/p/evaluation-of-machine-learning-classifiers</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/evaluation-of-machine-learning-classifiers</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Mon, 16 Jan 2023 06:42:17 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff6534d77-c4c4-4681-a288-193cfaaa6aa8_1920x1080.png" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-imag" target="_blank" href="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff6534d77-c4c4-4681-a288-193cfaaa6aa8_1920x1080.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff6534d77-c4c4-4681-a288-193cfaaa6aa8_1920x1080.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff6534d77-c4c4-4681-a288-193cfaaa6aa8_1920x1080.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff6534d77-c4c4-4681-a288-193cfaaa6aa8_1920x1080.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff6534d77-c4c4-4681-a288-193cfaaa6aa8_1920x1080.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff6534d77-c4c4-4681-a288-193cfaaa6aa8_1920x1080.png" width="1456" height="819" data-attrs="{&quot;src&quot;:&quot;https://substack-post-media.s3.amazonaws.com/public/images/f6534d77-c4c4-4681-a288-193cfaaa6aa8_1920x1080.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:819,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:1010247,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff6534d77-c4c4-4681-a288-193cfaaa6aa8_1920x1080.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff6534d77-c4c4-4681-a288-193cfaaa6aa8_1920x1080.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff6534d77-c4c4-4681-a288-193cfaaa6aa8_1920x1080.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff6534d77-c4c4-4681-a288-193cfaaa6aa8_1920x1080.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></div></div></a><figcaption class="image-caption">Figure 1: A depiction of Results from a Bias-Variance Analysis (Source: Author)</figcaption></figure></div><p></p><p>In the previous articles, we have discussed various Machine Learning methods for classification tasks. We have also used terms like <em>Regularization</em>, <em>Overfitting</em> and <em>Underfitting</em> repeatedly. In this article, we shall go through these terms in detail and show how you can circumvent such problems. Furthermore, we shall also discuss various metrics for measuring the performance of a classifier.</p><p></p> <p> <a href="https://azadacademy.substack.com/p/evaluation-of-machine-learning-classifiers"> Read more </a> </p> ]]>
</content:encoded>
</item>
<item>
<title>
<![CDATA[ ML Basics (Part-4): Decision Trees ]]>
</title>
<description>
<![CDATA[ What are Decision Trees, How to build and Apply Decision Trees for Different Classification Tasks ]]>
</description>
<link>https://azadacademy.substack.com/p/ml-basics-part-4-decision-trees</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/ml-basics-part-4-decision-trees</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Wed, 04 Jan 2023 09:11:47 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F153b1dd7-a471-443a-b0a2-7a347c4c800a_1280x929.png" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-imag" target="_blank" href="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F153b1dd7-a471-443a-b0a2-7a347c4c800a_1280x929.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F153b1dd7-a471-443a-b0a2-7a347c4c800a_1280x929.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F153b1dd7-a471-443a-b0a2-7a347c4c800a_1280x929.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F153b1dd7-a471-443a-b0a2-7a347c4c800a_1280x929.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F153b1dd7-a471-443a-b0a2-7a347c4c800a_1280x929.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F153b1dd7-a471-443a-b0a2-7a347c4c800a_1280x929.png" width="1280" height="929" data-attrs="{&quot;src&quot;:&quot;https://bucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com/public/images/153b1dd7-a471-443a-b0a2-7a347c4c800a_1280x929.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:929,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:160459,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F153b1dd7-a471-443a-b0a2-7a347c4c800a_1280x929.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F153b1dd7-a471-443a-b0a2-7a347c4c800a_1280x929.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F153b1dd7-a471-443a-b0a2-7a347c4c800a_1280x929.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F153b1dd7-a471-443a-b0a2-7a347c4c800a_1280x929.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></div></div></a><figcaption class="image-caption">Figure 1: Decision Tree Classifiers (Source: Author)</figcaption></figure></div><p></p><p>In the previous articles, we have explored the concepts of <em><a href="https://azadwolf.substack.com/p/ml-basics-part-1-regression-a-gateway">Regression</a></em>, <em><a href="https://azadwolf.substack.com/p/ml-basics-part-2-support-vector-machines">Support Vector Machines</a>, and <a href="https://azadwolf.substack.com/p/ml-basics-part-3-artificial-neural">Artificial Neural Networks</a>.</em> In this article, we shall go through another Machine Learning concept called, <em>Decision Trees</em>. You can check-out the other methods from the aforementioned links.</p><p></p> <p> <a href="https://azadacademy.substack.com/p/ml-basics-part-4-decision-trees"> Read more </a> </p> ]]>
</content:encoded>
</item>
<item>
<title>
<![CDATA[ ML Basics (Part-3): Artificial Neural Networks ]]>
</title>
<description>
<![CDATA[ An Easy Guide to ANNs and an Interactive Visualization Tool for Understanding and Learning the Concept ]]>
</description>
<link>https://azadacademy.substack.com/p/ml-basics-part-3-artificial-neural</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/ml-basics-part-3-artificial-neural</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Sun, 25 Dec 2022 09:00:56 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F145d72ef-bbb6-4fbe-91be-bc8c88e96dfc_1920x1080.png" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-imag" target="_blank" href="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F145d72ef-bbb6-4fbe-91be-bc8c88e96dfc_1920x1080.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F145d72ef-bbb6-4fbe-91be-bc8c88e96dfc_1920x1080.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F145d72ef-bbb6-4fbe-91be-bc8c88e96dfc_1920x1080.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F145d72ef-bbb6-4fbe-91be-bc8c88e96dfc_1920x1080.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F145d72ef-bbb6-4fbe-91be-bc8c88e96dfc_1920x1080.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F145d72ef-bbb6-4fbe-91be-bc8c88e96dfc_1920x1080.png" width="1456" height="819" data-attrs="{&quot;src&quot;:&quot;https://bucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com/public/images/145d72ef-bbb6-4fbe-91be-bc8c88e96dfc_1920x1080.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:819,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:314364,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F145d72ef-bbb6-4fbe-91be-bc8c88e96dfc_1920x1080.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F145d72ef-bbb6-4fbe-91be-bc8c88e96dfc_1920x1080.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F145d72ef-bbb6-4fbe-91be-bc8c88e96dfc_1920x1080.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F145d72ef-bbb6-4fbe-91be-bc8c88e96dfc_1920x1080.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></div></div></a><figcaption class="image-caption">Figure 1: Artificial Neural Network Interactive Tool for Visualization and Learning</figcaption></figure></div><p></p><p>In the previous posts, we have discussed <em><a href="https://azadwolf.substack.com/p/ml-basics-part-1-regression-a-gateway">Regression</a></em> and <em><a href="https://azadwolf.substack.com/p/ml-basics-part-2-support-vector-machines">Support Vector Machines (SVM)</a></em> as two important methods in Machine Learning. SVM has some similarity to a <em>Regression Analysis,</em> However, there is a method that is a direct descendent of a <em>Logistic Regression. </em>It is called &#8216;<em>Artificial Neural Network (ANN)</em>&#8217;. We shall build an ANN from scratch in this article, and you would be able to understand the concept with an interactive tool.</p> <p> <a href="https://azadacademy.substack.com/p/ml-basics-part-3-artificial-neural"> Read more </a> </p> ]]>
</content:encoded>
</item>
<item>
<title>
<![CDATA[ ML Basics (Part-2): Support Vector Machines ]]>
</title>
<description>
<![CDATA[ What are SVMs and How to Formulate, Build and Apply SVMs for Supervised Learning ]]>
</description>
<link>https://azadacademy.substack.com/p/ml-basics-part-2-support-vector-machines</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/ml-basics-part-2-support-vector-machines</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Mon, 12 Dec 2022 11:13:05 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4e38cde-63d7-4eaf-a8ff-a5aaf7174404_1920x1080.png" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-imag" target="_blank" href="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4e38cde-63d7-4eaf-a8ff-a5aaf7174404_1920x1080.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4e38cde-63d7-4eaf-a8ff-a5aaf7174404_1920x1080.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4e38cde-63d7-4eaf-a8ff-a5aaf7174404_1920x1080.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4e38cde-63d7-4eaf-a8ff-a5aaf7174404_1920x1080.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4e38cde-63d7-4eaf-a8ff-a5aaf7174404_1920x1080.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4e38cde-63d7-4eaf-a8ff-a5aaf7174404_1920x1080.png" width="1456" height="819" data-attrs="{&quot;src&quot;:&quot;https://bucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com/public/images/d4e38cde-63d7-4eaf-a8ff-a5aaf7174404_1920x1080.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:819,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:694551,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4e38cde-63d7-4eaf-a8ff-a5aaf7174404_1920x1080.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4e38cde-63d7-4eaf-a8ff-a5aaf7174404_1920x1080.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4e38cde-63d7-4eaf-a8ff-a5aaf7174404_1920x1080.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fd4e38cde-63d7-4eaf-a8ff-a5aaf7174404_1920x1080.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></div></div></a><figcaption class="image-caption">Figure 1: Depiction of a Support Vector Machine Model in an example of Soldiers at War (Source: Author)</figcaption></figure></div><p>In the previous post we learned about the Regression methods. In this article we shall go through a similar but slightly advanced machine learning method called &#8220;<em>Support Vector Machine (SVM)</em>&#8221;. Unless you are already familiar, it is advised that you check out the previous post first before reading this article.</p><p></p> <p> <a href="https://azadacademy.substack.com/p/ml-basics-part-2-support-vector-machines"> Read more </a> </p> ]]>
</content:encoded>
</item>
<item>
<title>
<![CDATA[ ML Basics (Part-1): REGRESSION — A Gateway Method to Machine Learning ]]>
</title>
<description>
<![CDATA[ An easy and comprehensive introduction to Linear, Non-Linear and Logistic Regression ]]>
</description>
<link>https://azadacademy.substack.com/p/ml-basics-part-1-regression-a-gateway</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/ml-basics-part-1-regression-a-gateway</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Sun, 04 Dec 2022 06:33:03 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fafe98afe-90f2-4702-a34d-18c33f1a591d_1920x1080.png" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-imag" target="_blank" href="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fafe98afe-90f2-4702-a34d-18c33f1a591d_1920x1080.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fafe98afe-90f2-4702-a34d-18c33f1a591d_1920x1080.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fafe98afe-90f2-4702-a34d-18c33f1a591d_1920x1080.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fafe98afe-90f2-4702-a34d-18c33f1a591d_1920x1080.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fafe98afe-90f2-4702-a34d-18c33f1a591d_1920x1080.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fafe98afe-90f2-4702-a34d-18c33f1a591d_1920x1080.png" width="1456" height="819" data-attrs="{&quot;src&quot;:&quot;https://bucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com/public/images/afe98afe-90f2-4702-a34d-18c33f1a591d_1920x1080.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:819,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:288908,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fafe98afe-90f2-4702-a34d-18c33f1a591d_1920x1080.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fafe98afe-90f2-4702-a34d-18c33f1a591d_1920x1080.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fafe98afe-90f2-4702-a34d-18c33f1a591d_1920x1080.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fafe98afe-90f2-4702-a34d-18c33f1a591d_1920x1080.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></div></div></a><figcaption class="image-caption">Figure 1: Examples of Linear, Non-Linear and Logistic Regression (Source: Author)</figcaption></figure></div><p><strong>Preface:</strong></p><p>There has been growing interest in the introductory posts on the elementary topics in Machine Learning. So, I am writing on such topics in the coming posts starting from this one. This article is mostly self-contained however, it requires basic understanding of <em>linear algebra</em>, and <em>calculus</em>.</p><p></p> <p> <a href="https://azadacademy.substack.com/p/ml-basics-part-1-regression-a-gateway"> Read more </a> </p> ]]>
</content:encoded>
</item>
<item>
<title>
<![CDATA[ Matters of Attention: What is Attention and How to Compute Attention in a Transformer Model ]]>
</title>
<description>
<![CDATA[ A comprehensive and easy guide to Attention in Transformer Models (with example code) ]]>
</description>
<link>https://azadacademy.substack.com/p/matters-of-attention-what-is-attention</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/matters-of-attention-what-is-attention</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Sun, 20 Nov 2022 05:25:03 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F4b2a0e6e-0434-4dec-9b9a-e01820fe80af_4000x2250.png" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-imag" target="_blank" href="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F4b2a0e6e-0434-4dec-9b9a-e01820fe80af_4000x2250.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F4b2a0e6e-0434-4dec-9b9a-e01820fe80af_4000x2250.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F4b2a0e6e-0434-4dec-9b9a-e01820fe80af_4000x2250.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F4b2a0e6e-0434-4dec-9b9a-e01820fe80af_4000x2250.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F4b2a0e6e-0434-4dec-9b9a-e01820fe80af_4000x2250.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F4b2a0e6e-0434-4dec-9b9a-e01820fe80af_4000x2250.png" width="1456" height="819" data-attrs="{&quot;src&quot;:&quot;https://bucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com/public/images/4b2a0e6e-0434-4dec-9b9a-e01820fe80af_4000x2250.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:819,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:577197,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F4b2a0e6e-0434-4dec-9b9a-e01820fe80af_4000x2250.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F4b2a0e6e-0434-4dec-9b9a-e01820fe80af_4000x2250.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F4b2a0e6e-0434-4dec-9b9a-e01820fe80af_4000x2250.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F4b2a0e6e-0434-4dec-9b9a-e01820fe80af_4000x2250.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></div></div></a><figcaption class="image-caption">Figure 1: Attention in a Transformer Model (Source: Author)</figcaption></figure></div><p>In this article, you will learn about Attention, its computation and role in a transformer network. &nbsp;You will also learn about vector embedding, position embedding and attention implementation in a text transformer. This will make use of concepts, &#8220;<em>Transformers</em>&#8221; and &#8220;<em>Autoencoders</em>&#8221;, so, if you would like to learn more about these topics then feel free to check out my earlier posts.</p> <p> <a href="https://azadacademy.substack.com/p/matters-of-attention-what-is-attention"> Read more </a> </p> ]]>
</content:encoded>
</item>
<item>
<title>
<![CDATA[ How to Improve Performance of a Diffusion Model by an Ensemble of Expert Models ]]>
</title>
<description>
<![CDATA[ A comprehensive explanation and review of the ensemble-based diffusion model from NVIDIA ]]>
</description>
<link>https://azadacademy.substack.com/p/how-to-improve-performance-of-a-diffusion</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/how-to-improve-performance-of-a-diffusion</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Sat, 12 Nov 2022 07:35:42 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fdefe8f35-fe52-4adb-9b69-b58169e3ab5c_4000x2250.png" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <p>In this article we shall go through a recent development in the Diffusion Model domain called <em>eDiff-I </em>[1]. It is an ensemble of Diffusion Models which seems to have outperformed all the other state-of-the-art (e.g., DALL-E2 and Stable Diffusion Model). This article will build upon earlier concepts (e.g., <em>Diffusion Models </em>and<em> Stable Diffusion Models</em>). Feel free to checkout my earlier posts on these topics.</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-imag" target="_blank" href="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fdefe8f35-fe52-4adb-9b69-b58169e3ab5c_4000x2250.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fdefe8f35-fe52-4adb-9b69-b58169e3ab5c_4000x2250.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fdefe8f35-fe52-4adb-9b69-b58169e3ab5c_4000x2250.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fdefe8f35-fe52-4adb-9b69-b58169e3ab5c_4000x2250.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fdefe8f35-fe52-4adb-9b69-b58169e3ab5c_4000x2250.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fdefe8f35-fe52-4adb-9b69-b58169e3ab5c_4000x2250.png" width="1456" height="819" data-attrs="{&quot;src&quot;:&quot;https://bucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com/public/images/defe8f35-fe52-4adb-9b69-b58169e3ab5c_4000x2250.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:819,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:555821,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fdefe8f35-fe52-4adb-9b69-b58169e3ab5c_4000x2250.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fdefe8f35-fe52-4adb-9b69-b58169e3ab5c_4000x2250.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fdefe8f35-fe52-4adb-9b69-b58169e3ab5c_4000x2250.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fdefe8f35-fe52-4adb-9b69-b58169e3ab5c_4000x2250.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></div></div></a><figcaption class="image-caption">Figure 1: Binary Tree Diagram Depicting an Ensemble of Diffusion Models being trained at Various Noise Levels (Source: Author)</figcaption></figure></div><p></p> <p> <a href="https://azadacademy.substack.com/p/how-to-improve-performance-of-a-diffusion"> Read more </a> </p> ]]>
</content:encoded>
</item>
<item>
<title>
<![CDATA[ Beyond Diffusion: What is Personalized Image Generation and How Can You Customize Image Synthesis? ]]>
</title>
<description>
<![CDATA[ Personalized Image Generation by Fine-Tuning the Stable Diffusion Models ]]>
</description>
<link>https://azadacademy.substack.com/p/beyond-diffusion-what-is-personalized</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/beyond-diffusion-what-is-personalized</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Mon, 17 Oct 2022 08:53:36 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F3178400f-a949-4ba0-9819-86e1c5295a63_4000x2250.jpeg" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-imag" target="_blank" href="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F3178400f-a949-4ba0-9819-86e1c5295a63_4000x2250.jpeg" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F3178400f-a949-4ba0-9819-86e1c5295a63_4000x2250.jpeg 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F3178400f-a949-4ba0-9819-86e1c5295a63_4000x2250.jpeg 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F3178400f-a949-4ba0-9819-86e1c5295a63_4000x2250.jpeg 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F3178400f-a949-4ba0-9819-86e1c5295a63_4000x2250.jpeg 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F3178400f-a949-4ba0-9819-86e1c5295a63_4000x2250.jpeg" width="1456" height="819" data-attrs="{&quot;src&quot;:&quot;https://bucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com/public/images/3178400f-a949-4ba0-9819-86e1c5295a63_4000x2250.jpeg&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:819,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:770467,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/jpeg&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F3178400f-a949-4ba0-9819-86e1c5295a63_4000x2250.jpeg 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F3178400f-a949-4ba0-9819-86e1c5295a63_4000x2250.jpeg 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F3178400f-a949-4ba0-9819-86e1c5295a63_4000x2250.jpeg 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F3178400f-a949-4ba0-9819-86e1c5295a63_4000x2250.jpeg 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></div></div></a><figcaption class="image-caption">Figure 1: Personalized Diffusion In Action (Source: Author)</figcaption></figure></div><p></p><p>In this article you will learn about customization and personalization of diffusion model based image generation. More specifically, you will learn about the <em>Textual-Inversion</em> and <em>Dream-Booth</em>. This article will build upon the concepts of <em>Autoencoders</em>, <em>Stable Diffusion Models (SD)</em> and <em>Transformers</em>. So, if you would like to know more about those concepts, feel free to checkout my earlier posts on these topics.</p><p></p> <p> <a href="https://azadacademy.substack.com/p/beyond-diffusion-what-is-personalized"> Read more </a> </p> ]]>
</content:encoded>
</item>
<item>
<title>
<![CDATA[ What is a Stable Diffusion Model and Why is it a Step Forward for Image Generation? ]]>
</title>
<description>
<![CDATA[ An Easy Guide to Latent Diffusion Models ]]>
</description>
<link>https://azadacademy.substack.com/p/what-is-a-stable-diffusion-model</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/what-is-a-stable-diffusion-model</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Mon, 03 Oct 2022 10:59:58 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F057f4031-7762-481d-a7ae-a5822f30df93_4000x2000.png" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-imag" target="_blank" href="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F057f4031-7762-481d-a7ae-a5822f30df93_4000x2000.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F057f4031-7762-481d-a7ae-a5822f30df93_4000x2000.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F057f4031-7762-481d-a7ae-a5822f30df93_4000x2000.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F057f4031-7762-481d-a7ae-a5822f30df93_4000x2000.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F057f4031-7762-481d-a7ae-a5822f30df93_4000x2000.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F057f4031-7762-481d-a7ae-a5822f30df93_4000x2000.png" width="1456" height="728" data-attrs="{&quot;src&quot;:&quot;https://bucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com/public/images/057f4031-7762-481d-a7ae-a5822f30df93_4000x2000.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:728,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:2319187,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F057f4031-7762-481d-a7ae-a5822f30df93_4000x2000.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F057f4031-7762-481d-a7ae-a5822f30df93_4000x2000.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F057f4031-7762-481d-a7ae-a5822f30df93_4000x2000.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F057f4031-7762-481d-a7ae-a5822f30df93_4000x2000.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></div></div></a><figcaption class="image-caption">Figure 1: Latent Diffusion Model (Base Diagram:[3], Concept-Map Overlay: Author)</figcaption></figure></div><p>In this article you will learn about a recent advancement in Image Generation domain. More specifically, you will learn about the <em>Latent Diffusion Models (LDM)</em> and their applications. This article will build upon the concepts of <em>GANs</em>, <em>Diffusion Models</em> and <em>Transformers</em>. So, if you would like to dig deeper into those concepts, feel free to checkout my earlier posts on these topics.</p><p></p> <p> <a href="https://azadacademy.substack.com/p/what-is-a-stable-diffusion-model"> Read more </a> </p> ]]>
</content:encoded>
</item>
<item>
<title>
<![CDATA[ What Are Vision Transformers And How Are They Important For General Purpose Learning? ]]>
</title>
<description>
<![CDATA[ Exploring The Concept and Experimenting with The Example Applications ]]>
</description>
<link>https://azadacademy.substack.com/p/what-are-vision-transformers-and</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/what-are-vision-transformers-and</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Sat, 20 Aug 2022 03:45:00 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Ffa0fb9b8-e8c5-4ab2-9ffb-74fe8ae49f65_1499x750.png" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-imag" target="_blank" href="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Ffa0fb9b8-e8c5-4ab2-9ffb-74fe8ae49f65_1499x750.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Ffa0fb9b8-e8c5-4ab2-9ffb-74fe8ae49f65_1499x750.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Ffa0fb9b8-e8c5-4ab2-9ffb-74fe8ae49f65_1499x750.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Ffa0fb9b8-e8c5-4ab2-9ffb-74fe8ae49f65_1499x750.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Ffa0fb9b8-e8c5-4ab2-9ffb-74fe8ae49f65_1499x750.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Ffa0fb9b8-e8c5-4ab2-9ffb-74fe8ae49f65_1499x750.png" width="1456" height="728" data-attrs="{&quot;src&quot;:&quot;https://bucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com/public/images/fa0fb9b8-e8c5-4ab2-9ffb-74fe8ae49f65_1499x750.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:728,&quot;width&quot;:1456,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:1004549,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Ffa0fb9b8-e8c5-4ab2-9ffb-74fe8ae49f65_1499x750.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Ffa0fb9b8-e8c5-4ab2-9ffb-74fe8ae49f65_1499x750.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Ffa0fb9b8-e8c5-4ab2-9ffb-74fe8ae49f65_1499x750.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Ffa0fb9b8-e8c5-4ab2-9ffb-74fe8ae49f65_1499x750.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></div></div></a><figcaption class="image-caption">Figure 1: Vision Transformers in Action (Source: Author)</figcaption></figure></div><p></p><p>There has been a significant advancement in the field of AI in the past several years. Generative models have been the most successful in the vision domain however, they are built for highly specialized tasks. These specialized learning models require reconstruction or retraining whenever the task is changed. Therefore, the interest in General purpose learning models is increasing. One of such type of models is called Transformers. In this article, we briefly discuss:</p><ul><li><p>What is a Transformer?</p></li><li><p>What is a Vision Transformer (ViT)?</p></li><li><p>What are the various applications of ViTs?</p></li><li><p>How can ViTs be used for general purpose learning?</p><p></p></li></ul> <p> <a href="https://azadacademy.substack.com/p/what-are-vision-transformers-and"> Read more </a> </p> ]]>
</content:encoded>
</item>
<item>
<title>
<![CDATA[ Diffusion Models Made Easy ]]>
</title>
<description>
<![CDATA[ An Easy Introduction to Denoising Diffusion Probabilistic Models ]]>
</description>
<link>https://azadacademy.substack.com/p/diffusion-models-made-easy</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/diffusion-models-made-easy</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Wed, 03 Aug 2022 03:33:00 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F2c77897e-e43a-43fd-8b5d-7ff246ac206d_1280x720.png" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-imag" target="_blank" href="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F2c77897e-e43a-43fd-8b5d-7ff246ac206d_1280x720.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F2c77897e-e43a-43fd-8b5d-7ff246ac206d_1280x720.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F2c77897e-e43a-43fd-8b5d-7ff246ac206d_1280x720.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F2c77897e-e43a-43fd-8b5d-7ff246ac206d_1280x720.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F2c77897e-e43a-43fd-8b5d-7ff246ac206d_1280x720.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F2c77897e-e43a-43fd-8b5d-7ff246ac206d_1280x720.png" width="1280" height="720" data-attrs="{&quot;src&quot;:&quot;https://bucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com/public/images/2c77897e-e43a-43fd-8b5d-7ff246ac206d_1280x720.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:720,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:70972,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F2c77897e-e43a-43fd-8b5d-7ff246ac206d_1280x720.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F2c77897e-e43a-43fd-8b5d-7ff246ac206d_1280x720.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F2c77897e-e43a-43fd-8b5d-7ff246ac206d_1280x720.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F2c77897e-e43a-43fd-8b5d-7ff246ac206d_1280x720.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></div></div></a><figcaption class="image-caption">Figure 1: Process of Denoising Diffusion Probabilistic Model (Source: Author)</figcaption></figure></div><p></p> <p> <a href="https://azadacademy.substack.com/p/diffusion-models-made-easy"> Read more </a> </p> ]]>
</content:encoded>
</item>
<item>
<title>
<![CDATA[ Draw the Desire: Bringing the sketches to life using Deep Learning ]]>
</title>
<description>
<![CDATA[ An Easy Practical Introduction to Conditional GANs ]]>
</description>
<link>https://azadacademy.substack.com/p/draw-the-desire-bringing-the-sketches</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/draw-the-desire-bringing-the-sketches</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Sat, 30 Jul 2022 03:17:00 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd1f9f2-99d1-40e7-b600-af616e907946_1280x720.png" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <p>In this article, you will learn about conditional GAN (Generative Adversarial Network) and will be able to build one from scratch. After that you will be able to apply the cGAN model on a fashion products dataset for converting sketches of products to color images. If you would like to understand what are GANs [1] you can check out our previous tutorials on Latent Spaces.</p><p></p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-imag" target="_blank" href="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd1f9f2-99d1-40e7-b600-af616e907946_1280x720.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd1f9f2-99d1-40e7-b600-af616e907946_1280x720.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd1f9f2-99d1-40e7-b600-af616e907946_1280x720.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd1f9f2-99d1-40e7-b600-af616e907946_1280x720.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd1f9f2-99d1-40e7-b600-af616e907946_1280x720.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd1f9f2-99d1-40e7-b600-af616e907946_1280x720.png" width="1280" height="720" data-attrs="{&quot;src&quot;:&quot;https://bucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com/public/images/6bd1f9f2-99d1-40e7-b600-af616e907946_1280x720.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:720,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:639787,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd1f9f2-99d1-40e7-b600-af616e907946_1280x720.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd1f9f2-99d1-40e7-b600-af616e907946_1280x720.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd1f9f2-99d1-40e7-b600-af616e907946_1280x720.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F6bd1f9f2-99d1-40e7-b600-af616e907946_1280x720.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></div></div></a><figcaption class="image-caption">Figure 1: An example output of the GAN network trained on Fashion Products</figcaption></figure></div> <p> <a href="https://azadacademy.substack.com/p/draw-the-desire-bringing-the-sketches"> Read more </a> </p> ]]>
</content:encoded>
</item>
<item>
<title>
<![CDATA[ TerrificEye: An Edge Computing System For Traffic Analytics From Videos ]]>
</title>
<description>
<![CDATA[ How to build a real-time, standalone traffic monitoring and analytics system ]]>
</description>
<link>https://azadacademy.substack.com/p/terrificeye-an-edge-computing-system</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/terrificeye-an-edge-computing-system</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Wed, 20 Jul 2022 03:05:00 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F99d5952b-8c76-4782-8182-8c9e24fa8a67_908x512.gif" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-imag" target="_blank" href="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F99d5952b-8c76-4782-8182-8c9e24fa8a67_908x512.gif" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F99d5952b-8c76-4782-8182-8c9e24fa8a67_908x512.gif 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F99d5952b-8c76-4782-8182-8c9e24fa8a67_908x512.gif 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F99d5952b-8c76-4782-8182-8c9e24fa8a67_908x512.gif 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F99d5952b-8c76-4782-8182-8c9e24fa8a67_908x512.gif 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F99d5952b-8c76-4782-8182-8c9e24fa8a67_908x512.gif" width="908" height="512" data-attrs="{&quot;src&quot;:&quot;https://bucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com/public/images/99d5952b-8c76-4782-8182-8c9e24fa8a67_908x512.gif&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:512,&quot;width&quot;:908,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:2560962,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/gif&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F99d5952b-8c76-4782-8182-8c9e24fa8a67_908x512.gif 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F99d5952b-8c76-4782-8182-8c9e24fa8a67_908x512.gif 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F99d5952b-8c76-4782-8182-8c9e24fa8a67_908x512.gif 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F99d5952b-8c76-4782-8182-8c9e24fa8a67_908x512.gif 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></div></div></a><figcaption class="image-caption">Figure 1: TerrificEye System (Source: Author)</figcaption></figure></div><p></p> <p> <a href="https://azadacademy.substack.com/p/terrificeye-an-edge-computing-system"> Read more </a> </p> ]]>
</content:encoded>
</item>
<item>
<title>
<![CDATA[ Why Is Cross Entropy Equal to KL-Divergence? ]]>
</title>
<description>
<![CDATA[ Exploring the Concepts of Entropy, Cross-Entropy and KL-Divergence ]]>
</description>
<link>https://azadacademy.substack.com/p/why-is-cross-entropy-equal-to-kl</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/why-is-cross-entropy-equal-to-kl</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Fri, 15 Jul 2022 02:50:00 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fea34c931-0fcf-4dba-8f18-e4375f30b308_640x597.png" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-imag" target="_blank" href="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fea34c931-0fcf-4dba-8f18-e4375f30b308_640x597.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fea34c931-0fcf-4dba-8f18-e4375f30b308_640x597.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fea34c931-0fcf-4dba-8f18-e4375f30b308_640x597.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fea34c931-0fcf-4dba-8f18-e4375f30b308_640x597.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fea34c931-0fcf-4dba-8f18-e4375f30b308_640x597.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fea34c931-0fcf-4dba-8f18-e4375f30b308_640x597.png" width="640" height="597" data-attrs="{&quot;src&quot;:&quot;https://bucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com/public/images/ea34c931-0fcf-4dba-8f18-e4375f30b308_640x597.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:597,&quot;width&quot;:640,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:29070,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fea34c931-0fcf-4dba-8f18-e4375f30b308_640x597.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fea34c931-0fcf-4dba-8f18-e4375f30b308_640x597.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fea34c931-0fcf-4dba-8f18-e4375f30b308_640x597.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2Fea34c931-0fcf-4dba-8f18-e4375f30b308_640x597.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></div></div></a><figcaption class="image-caption">Figure 1: Two probability distributions sampled from normal distribution (Image by author)</figcaption></figure></div><p></p><p>It is a common practice to use cross-entropy in the loss function while constructing a Generative Adversarial Network [1] even though original concept suggests the use of KL-divergence. This creates confusion often for the person new to the field. In this article we go through the concepts of entropy, cross-entropy and Kullback-Leibler Divergence [2] and see how they can be approximated to be equal.</p><p></p> <p> <a href="https://azadacademy.substack.com/p/why-is-cross-entropy-equal-to-kl"> Read more </a> </p> ]]>
</content:encoded>
</item>
<item>
<title>
<![CDATA[ A Practical Introduction to Deep Convolutional Generative Adversarial Network (DCGAN) ]]>
</title>
<description>
<![CDATA[ In the previous tutorial we learned about variational autoencoders and their implementation in TensorFlow. ]]>
</description>
<link>https://azadacademy.substack.com/p/a-practical-introduction-to-deep</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/a-practical-introduction-to-deep</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Thu, 30 Jun 2022 01:58:00 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F107bb5f2-224f-4ba8-a682-6dc70b702309_1096x544.png" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <p>In the previous tutorial we learned about variational autoencoders and their implementation in TensorFlow. In this tutorial, we shall explore another deep learning architecture called Generative Adversarial Network (GAN).</p><div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-imag" target="_blank" href="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F107bb5f2-224f-4ba8-a682-6dc70b702309_1096x544.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F107bb5f2-224f-4ba8-a682-6dc70b702309_1096x544.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F107bb5f2-224f-4ba8-a682-6dc70b702309_1096x544.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F107bb5f2-224f-4ba8-a682-6dc70b702309_1096x544.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F107bb5f2-224f-4ba8-a682-6dc70b702309_1096x544.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F107bb5f2-224f-4ba8-a682-6dc70b702309_1096x544.png" width="1096" height="544" data-attrs="{&quot;src&quot;:&quot;https://bucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com/public/images/107bb5f2-224f-4ba8-a682-6dc70b702309_1096x544.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:544,&quot;width&quot;:1096,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:539835,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F107bb5f2-224f-4ba8-a682-6dc70b702309_1096x544.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F107bb5f2-224f-4ba8-a682-6dc70b702309_1096x544.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F107bb5f2-224f-4ba8-a682-6dc70b702309_1096x544.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F107bb5f2-224f-4ba8-a682-6dc70b702309_1096x544.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></div></div></a><figcaption class="image-caption">Figure 1: An example output of a DCGAN trained on Bicycles Dataset</figcaption></figure></div><p></p> <p> <a href="https://azadacademy.substack.com/p/a-practical-introduction-to-deep"> Read more </a> </p> ]]>
</content:encoded>
</item>
<item>
<title>
<![CDATA[ What are Variational Autoencoders? ]]>
</title>
<description>
<![CDATA[ A Practical Introduction to Variational Autoencoders ]]>
</description>
<link>https://azadacademy.substack.com/p/what-are-variational-autoencoders</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/what-are-variational-autoencoders</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Tue, 31 May 2022 07:37:20 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F858cefae-70eb-4410-8b78-e1383473b33d_1280x720.png" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <div class="captioned-image-container"><figure><a class="image-link image2 is-viewable-imag" target="_blank" href="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F858cefae-70eb-4410-8b78-e1383473b33d_1280x720.png" data-component-name="Image2ToDOM"><div class="image2-inset"><picture><source type="image/webp" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F858cefae-70eb-4410-8b78-e1383473b33d_1280x720.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F858cefae-70eb-4410-8b78-e1383473b33d_1280x720.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F858cefae-70eb-4410-8b78-e1383473b33d_1280x720.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_webp,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F858cefae-70eb-4410-8b78-e1383473b33d_1280x720.png 1456w" sizes="100vw"><img src="https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F858cefae-70eb-4410-8b78-e1383473b33d_1280x720.png" width="1280" height="720" data-attrs="{&quot;src&quot;:&quot;https://bucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com/public/images/858cefae-70eb-4410-8b78-e1383473b33d_1280x720.png&quot;,&quot;srcNoWatermark&quot;:null,&quot;fullscreen&quot;:null,&quot;imageSize&quot;:null,&quot;height&quot;:720,&quot;width&quot;:1280,&quot;resizeWidth&quot;:null,&quot;bytes&quot;:706318,&quot;alt&quot;:null,&quot;title&quot;:null,&quot;type&quot;:&quot;image/png&quot;,&quot;href&quot;:null,&quot;belowTheFold&quot;:false,&quot;topImage&quot;:true,&quot;internalRedirect&quot;:null,&quot;isProcessing&quot;:false}" class="sizing-normal" alt="" srcset="https://substackcdn.com/image/fetch/w_424,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F858cefae-70eb-4410-8b78-e1383473b33d_1280x720.png 424w, https://substackcdn.com/image/fetch/w_848,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F858cefae-70eb-4410-8b78-e1383473b33d_1280x720.png 848w, https://substackcdn.com/image/fetch/w_1272,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F858cefae-70eb-4410-8b78-e1383473b33d_1280x720.png 1272w, https://substackcdn.com/image/fetch/w_1456,c_limit,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F858cefae-70eb-4410-8b78-e1383473b33d_1280x720.png 1456w" sizes="100vw" fetchpriority="high"></picture><div class="image-link-expand"><svg xmlns="http://www.w3.org/2000/svg" width="20" height="20" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="lucide lucide-maximize2"><polyline points="15 3 21 3 21 9"></polyline><polyline points="9 21 3 21 3 15"></polyline><line x1="21" x2="14" y1="3" y2="10"></line><line x1="3" x2="10" y1="21" y2="14"></line></svg></div></div></a><figcaption class="image-caption">Figure 1: An example output of a Variational autoencoder </figcaption></figure></div><p></p><p>In the previous tutorial (<a href="https://medium.com/mlearning-ai/latent-space-representation-a-hands-on-tutorial-on-autoencoders-in-tensorflow-57735a1c0f3f">https://medium.com/mlearning-ai/latent-space-representation-a-hands-on-tutorial-on-autoencoders-in-tensorflow-57735a1c0f3f</a>) we learned about latent spaces, autoencoders and their implementation in TensorFlow. In this tutorial, we shall extend the concept of autoencoders and look at one of the special cases of autoencoders called variational autoencoders.</p><p></p> <p> <a href="https://azadacademy.substack.com/p/what-are-variational-autoencoders"> Read more </a> </p> ]]>
</content:encoded>
</item>
<item>
<title>
<![CDATA[ LATENT SPACE REPRESENTATION ]]>
</title>
<description>
<![CDATA[ A HANDS-ON TUTORIAL ON AUTOENCODERS IN TENSORFLOW ]]>
</description>
<link>https://azadacademy.substack.com/p/latent-space-representation</link>
<guid isPermaLink="true">https://azadacademy.substack.com/p/latent-space-representation</guid>
<dc:creator>
<![CDATA[ Dr. J. Rafid Siddiqui ]]>
</dc:creator>
<pubDate>Thu, 19 May 2022 09:48:51 GMT</pubDate>
<enclosure url="https://substackcdn.com/image/fetch/f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com%2Fpublic%2Fimages%2F8650a62a-3c04-46dc-bc46-6c7b329d9bc8_772x352.png" length="0" type="image/jpeg"/>
<content:encoded>
<![CDATA[ <p>This is a part-1 of the series of tutorials that I am writing on unsupervised/self-supervised learning using deep neural networks. This would cover the following topics:</p><p>&#183;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Autoencoders</p><p>&#183;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Variational Autoencoders</p><p>&#183;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp;&nbsp; Generative Adversarial Networks</p><p>In this tutorial, the focus would be on latent space implementation using autoencoder architecture and its visualization using t-SNE embedding. Before we delve into code, lets define some important concepts which we will encounter throughout the tutorial.</p><p></p> <p> <a href="https://azadacademy.substack.com/p/latent-space-representation"> Read more </a> </p> ]]>
</content:encoded>
</item>
</channel>
</rss>