Generative Adversarial Networks or GAN, one of the interesting advents of the decade, has been used to create arts, fake images, and swapping faces in videos, among others. GANs are the subclass of deep generative models which aim to learn a target distribution in an unsupervised manner. The resources we listed below will help a beginner to kick-start learning and understanding how this model works.
In this article, we list down 10 free resources to learn GAN in 2020.
Note: The list is in alphabetical order
1| Are GANs Created Equal? A Large-Scale Study
Resource: Paper
About: ‘Are GANs Created Equal? A Large-Scale Study’ is a paper written by the researchers at Google Brain. In this paper, you will learn about the subclass of generative models called Generative adversarial networks (GAN). The researchers conducted a neutral, multi-faceted large-scale empirical study on state-of-the-art models and evaluation measures. Further, the researchers proposed several datasets to evaluate precision and recall.
Click here to read.
2| A Large-Scale Study on Regularization and Normalization in GANs
Resource: Paper
About: To understand this paper, you will need to have a basic understanding of what GAN is. The researchers explained the class of deep generative models from a practical perspective. Further, they discussed and evaluated the common pitfalls and reproducibility issues while working on GAN.
Click here to read.
3| Deep Diving into GANs: From Theory To Production
Resource: Blog
About: Deep Diving into GANs is a guide where you will learn the very basics of what a GAN is, understand the use of TensorFlow, APIs, and Google cloud functions. You will learn topics like conditional GAN, its applications, generators, discriminators, non-saturating value function, gradient ascent, writing a GAN using AshPy and TensorFlow Datasets, along with much more. This tutorial requires packages like Python 3.7 or more, TensorFlow 2.0 or more, Jupyter and NumPy.
Click here to read.
4| GAN by Ian Goodfellow
Resource: Video
About: This is a NIPS 2016 video tutorial where Ian Goodfellow explained the basics of Generative adversarial networks (GANs). The topics in this video include the review of work applying GANs to large image generation, extending the GAN framework to approximate maximum likelihood rather than minimizing the Jensen-Shannon divergence, semi-supervised learning with GANs, and other such.
Click here to watch.
5| Generative Models By OpenAI
Resource: Blog
About: In this blog by OpenAI, you will learn about generative models and how to train them. It covers topics like training a generative model, process of generating images, examples of generative model approaches and how it works.
Click here to read.
6| GANs In Action
Resource: Book (Free Preview)
About: GANs in Action is one of the popular books of GAN written by Jakub Langr and Vladimir Bok. In this book, you will learn how to build and train your own Generative Adversarial Networks (GANs), understand generators and discriminators, how to build your own simple adversarial system and much more.
Click here to read.
7| Generative Adversarial Networks
Resource: Paper
About: This paper introduces General Adversarial Network (GAN). Here, you will learn the generative model and discriminative model and how they work. Ian Goodfellow and his team discussed adversarial nets, advantages, and disadvantages of GAN and other such.
Click here to read.
8| Generative Adversarial Networks: An Overview
Resource: Paper
About: In this paper, you will get an overview of GANs for the signal processing community as well as drawing on familiar analogies and other concepts. You will understand how to identify different methods for training and constructing GANs, and their challenges.
Click here to read.
9| Introduction to GAN By Google
Resource: Blog
About: This tutorial is provided by the researchers at Google. Here, you will learn the basics of GAN and how to use the TF-GAN library to create GANs. You will understand the difference between generative and discriminative models, understand the advantages and disadvantages of common GAN loss functions, and much more.
Click here to read.
10| Lecture Notes On Generative Learning Algorithms By Andrew NG
Resource: PDF
About: This lecture notes by Andrew NG from Stanford University will help you understand topics like Gaussian discriminant analysis, understanding GDA model and logistic regression, Laplace smoothing, Naive Bayes, event models for text classification, and other such related topics.
Click here to read.