IIT Madras · Computer Science

Deep Learning - Part 2

Prof. Mitesh M. Khapra · 37 free video lectures

37 video lectures. Topics: Recap of Probability Theory; Why are we interested in Joint Distributions; How do we represent a joint distribution; Can we represent the joint distribution more compactly; Can we use a graph to represent a joint distribution; Different types of reasoning encoded in a…

▶ Play on Open Lecture HallCourse page ↗

Lectures

  1. Recap of Probability Theory
  2. Why are we interested in Joint Distributions
  3. How do we represent a joint distribution
  4. Can we represent the joint distribution more compactly
  5. Can we use a graph to represent a joint distribution
  6. Different types of reasoning encoded in a Bayesian Network
  7. Independencies encoded by a Bayesian Network(Case 1: Node and it's parents)
  8. Independencies encoded by a Bayesian Network(Case 2: Node and it's non-parents)
  9. Independencies encoded by a Bayesian Network(Case 3: Node and it's descendants)
  10. Bayesian Networks : Formal Semantics
  11. I-Maps
  12. Markov Networks: Motivation
  13. Factors in Markov Network
  14. Local Independencies in a Markov Network
  15. Joint Distributions
  16. The concept of a latent variable
  17. Restricted Boltzmann Machines
  18. RBMs as Stochastic Neural Networks
  19. Unsupervised Learning with RBMs
  20. Computing the gradient of the log likelihood
  21. Motivation for Sampling
  22. Motivation for Sampling - Part - 02
  23. Markov Chains
  24. Why de we care about Markov Chains ?
  25. Setting up a Markov Chain for RBMs
  26. Training RBMs Using Gibbs Sampling
  27. Training RBMS Using Contrastive Divergence
  28. Revisiting Autoencoders
  29. Variational Autoencoders: The Neural Network Perspective
  30. Variational Autoencoders: The Graphical model perspective
  31. Neural Autoregressive Density Estimator
  32. Masked Autoencoder Density Estimator (MADE)
  33. Generative Adversarial Networks - The Intuition
  34. Generative Adversarial Networks - Architecture
  35. Generative Adversarial Networks - The Math Behind it
  36. Generative Adversarial Networks - Some Cool Stuff and Applications
  37. Bringing it all together (the deep generative summary)

From NPTEL (IITs and IISc) · CC BY-NC-SA. More from IIT Madras.

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