Generative Adversarial Networks (GAN) Course for Beginners

Introduction:

Generative models are gaining a lot of popularity recently among data scientists, mainly because they facilitate the building of AI systems that consume raw data from a source and automatically builds an understanding of it. Unlike supervised learning methods, generative models do not require labelled data.

Generative adversarial networks (GANs) are a special class of generative models introduced by Ian Goodfellow in 2014. In GAN, a generator function learns to synthesize samples that best resemble some dataset, while a discriminator function learns to distinguish between samples drawn from the dataset and samples synthesized by the generator. GANs have emerged as a promising framework for unsupervised learning: GAN generators are able to produce images of unprecedented visual quality, while GAN discriminators learn features with rich semantics that lead to state-of-the-art semi-supervised learning.

Course Objectives:

  • Generative model using Auto Encoder
  • GAN Architecture
  • GAN Implementation on MNIST dataset
  • Style Transfer with GAN
  • Image Generation with GAN

Duration

7 hours, 1 Day Course

Mode of Delivery

Classroom-based, Instructor-led Training

Course Outlines

  1. Overview of Generative Models
    1. What is Generative Models
    2. Application of Generative Models
    3. Types of Generative Models
    4. Online Generative Model Demo with Sketch-RNN
    5. Installing Google Colab
  2. DeepDream
    1. Recap on Convolutional Neural Networks (CNN)
    2. Recap on Transfer Learning
    3. What is DeepDream?
    4. DeepDream Applications
    5. DeepDream Implementation
  3. Neural Style Transfer
    1. What is Neural Style Transfer?
    2. Neural Style Transfer Applications
    3. Neural Style Transfer Implementation
  4. Variational Autoencoder (VAE)
    1. What is Autoencoder
    2. Variational Autoencoder (VAE)
    3. VAE Implementation
  5. Generative Adversarial Networks (GAN)
    1. What is GAN?
    2. GAN Applications
    3. Basic DCGAN Architecture
    4. DCGAN Implementation
    5. GAN Challenges and Tricks
  6. Text Generation
    1. Recap on Recurrent Neural Networks (RNN)
    2. Recap on Long Short Term Memory (LSTM)
    3. Char by Char Text Generation with LSTM