Syllabus
Unit 1
Introduction to Generative AI, Autoencoders – Representational power, layer size and depth, Undercomplete autoencoders, Denoising autoencoders, Contractive autoencoders, Variational autoencoders, Case study: Applications of autoencoders in dimension reduction.
Unit 2
Generative Adversarial networks (GAN) – structure and training algorithm, Deep Convolutional GAN, Autoregressive models – Finite memory, long range memory through RNN and CNN, Transformers – Encoder, decoders, scaling laws, Case study: Generative Adversarial Networks-aided Intrusion Detection System.
Unit 3
Structured probabilistic models – Issues of unstructured models, Directed and Undirected Graphs to describe the models, Partition function, separation and D-separation, Conversion of graphs, sampling from graphical models, Case study: Restricted Boltzmann machine.
Objectives and Outcomes
Course Objectives
- This course covers the mathematical and computational foundations of generative modeling, as well as applications.
- Specific topics include variational autoencoders, generative adversarial networks, autoregressive models such as Transformers, normalizing flow models, information lattice learning, neural text decoding, prompt programming, and detection of generated content.
Course Outcomes
CO1: Understand principles of Generative AI and their applications.
CO2: Analyze Autoencoder and transformer in real-world scenarios.
CO3: Analyze GAN architectures and applications.
CO4: Analyze graphs for probabilistic models.
CO-PO Mapping
| PO/PSO |
PO1 |
PO2 |
PO3 |
PO4 |
PO5 |
PO6 |
PO7 |
PO8 |
PO9 |
PO10 |
PO11 |
PO12 |
PSO1 |
PSO2 |
| CO |
| CO1 |
3 |
3 |
3 |
3 |
2 |
0 |
3 |
2 |
2 |
2 |
0 |
0 |
3 |
3 |
| CO2 |
3 |
3 |
3 |
3 |
3 |
0 |
3 |
2 |
2 |
2 |
0 |
0 |
3 |
3 |
| CO3 |
3 |
3 |
3 |
3 |
3 |
0 |
3 |
2 |
2 |
2 |
0 |
0 |
3 |
3 |
| CO4 |
3 |
3 |
3 |
3 |
3 |
0 |
3 |
2 |
2 |
2 |
0 |
0 |
3 |
3 |
Evaluation Pattern
Evaluation Pattern: 70:30
| Assessment |
Internal |
End Semester |
| Midterm |
20 |
|
| Continuous Assessment – Theory (*CAT) |
10 |
|
| Continuous Assessment – Lab (*CAL) |
40 |
|
| **End Semester |
|
30 (50 Marks; 2 hours exam)
|
*CAT – Can be Quizzes, Assignments, and Reports
*CAL – Can be Lab Assessments, Project, and Report
**End Semester can be theory examination/ lab-based examination/ project presentation
Text Books / References
Textbook(s)
I.Goodfellow, Y. Bengio, and A. Courville, “Deep Learning”, MIT Press, 2016.
Reference(s)
Raut, R., Pathak, P. D., Sakhare, S. R., & Patil, S. (Eds.), “Generative Adversarial Networks and Deep Learning: Theory and Applications”. CRC Press, 2023.
J.M. Tomcsak, “Deep Generative Modeling”, Springer, 2022.
Langr J, Bok V. “GANs in action: deep learning with generative adversarial networks”. Manning. 2019.
A.Papoulis and S. U. Pillai, “Probability – Random Variables, and Stochastic Processes”, Fourth Edition, McGraw-Hill, 2017.
