Course

Unit 1

Generative Modeling, Generative Versus Discriminative Modeling, Generative Model Taxonomy, Deep Neural Networks, Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Autoencoders, Variational Autoencoders, Exploring the Latent Space.

Unit 2

Generative Adversarial Networks, Deep Convolutional GAN (DCGAN), Wasserstein GAN with Gradient Penalty, Conditional GAN (CGAN).

Unit 3

Recurrent Neural Network , Long Short-Term Memory Network (LSTM), Recurrent Neural Network (RNN) Extensions. Normalizing Flow Models, Energy-Based Models, Diffusion Models, Transformers. Applications of Generative AI to text and image generation.

Prerequisite(s)

Machine Learning

Course Objectives

• To introduce artificial neural networks and their architecture?
• To introduce techniques used for training artificial neural networks?
• To enable design of deep learning models for classification and sequence analysis?

Course Outcomes?

1. CO1: Able to understand different types of neural network architectures used in Generative AI.? 
2. CO2: Able to understand the mathematics behind design of Generative AI models .? 
3. CO3: Able to design models for Generative AI
4. CO4: Able to implement deep learning models for Generative AI applications? 

CO – PO Mapping

Text Book(s)

David Foster , Generative Deep Learning: Teaching Machines To Paint, Write, Compose, and Play, 2nd Edition, O’Reilley (Grayscale Indian Edition), 2023

Reference(s)

Joseph Babcock, Raghav Bali , Generative AI with Python and TensorFlow 2: Create images, text, and music with VAEs, GANs, LSTMs, Transformer models, Packt Publishers, 2021.