IISc Bangalore PES University RV University · Computer Science

Fundamentals of Generative AI and Large Language Models: Theory and Practice

Prof. Sriram Ganapathy,, Prof. Ashwini Kodipalli,, Prof. Baishali Garai · 74 free video lectures

This course provides a rigorous exploration of modern generative AI, covering latent-variable models such as Autoencoders, VAEs, GANs, and Diffusion Models that form the backbone of contemporary generative systems. Learners will develop a deep understanding of probabilistic modeling, adversarial…

▶ Play on Open Lecture HallCourse page ↗

Lectures

  1. Introduction to Generative AI
  2. Activation Functions & Loss Functions in Deep Learning
  3. Optimizers - Part A
  4. Optimizers - Part B
  5. Convolutional Neural Network - Part A
  6. Convolutional Neural Network - Part B
  7. Introduction to Google Colab
  8. Practical Exercise - 1
  9. Practical Exercise - 2
  10. Introduction to Autoencoder
  11. Training objective: Reconstruction Loss (MSE, Binary Cross-Entropy)
  12. Types of Autoencoders: Architecture and Code-Level Understanding
  13. Regularization Techniques in AE: Denoising
  14. Regularization Techniques in AE: Sparse
  15. Regularization Techniques in AE: Contractive
  16. Numerical Example, Limitations of AE
  17. Practical Exercise - 1
  18. Practical Exercise - 2
  19. Intuition behind KL Divergence - Part A
  20. Intuition behind KL Divergence - Part B
  21. Introduction to VAE and the working of the Encoder
  22. Working of Probabilistic Decoder, ELBO, Loss Function of VAE
  23. Reparameterization Trick
  24. Numerical Example
  25. Practical Exercise - 1
  26. Entanglement, Disentanglement Latent Space, and Beta-VAE
  27. Conditional VAE
  28. Latent Space Interpolation
  29. Practical Exercise - 2
  30. Practical Exercise - 3
  31. Motivation for GANs
  32. GAN Architecture
  33. GAN Objective and Loss Functions
  34. GAN Convergence and Nash equilibrium
  35. Introduction to DCGAN
  36. Practical Exercise - 1
  37. Practical Exercise - 2
  38. Conditional GAN
  39. Pix2Pix GAN
  40. Cycle GAN
  41. Style GAN
  42. Style GAN 2
  43. Practical Exercise - 1
  44. Introduction to Diffusion Model
  45. Mathematics of Diffusion Models
  46. "Denoising Diffusion Probabilistic Model- Forward Process"
  47. "Denoising Diffusion Probabilistic Model- Reverse Process"
  48. Hand on on forward Diffusion process
  49. U-Net for Denoising
  50. Classifier Guided Diffusion Model
  51. Classifier free Diffusion Models
  52. Stable Diffusion Model
  53. Hands-on on reverse diffusion process
  54. Foundations of Natural Language Processing
  55. Sequential Modeling with RNNs and LSTM
  56. Evolution From LSTMs to Transformers
  57. Transformer Architecture: Encoder
  58. Practical Exercise - 1
  59. Transformer Architecture: Decoder
  60. Bidirectional Encoder Representations from Transformer (BERT)
  61. Generative Pre-trained Transformer (GPT) Decoder-only Large Language Model
  62. Prompt Engineering Basics
  63. Hands-on on LLM
  64. LLMs – Recap
  65. In-context Learning
  66. Low-Rank Adaptation (LoRA)
  67. RAG Principle
  68. RAG Recent Advances
  69. Tutorial on In-context Learning, RAG and LoRA
  70. LLMs for Text Generation
  71. LLMs for Audio, Video and Multimodal Tasks
  72. Size vs Performance and Benchmarking
  73. Bias, Fairness and Safety
  74. Tutorial on LLMs, Multimodal LLMs, Bias, Fairness, Evaluation and Safety

From NPTEL (IITs and IISc) · CC BY-NC-SA. More from IISc Bangalore PES University RV University.

Open Lecture Hall is free, with no ads and no sign-up. It is not run by or connected to any university; the lectures are the universities' own free recordings, played from where they host them. About & rights