L10b Representation learning and deep generative modelling

Lecture slides (Lect 10b Download Lect 10b)

Date and venue: Feb 21, kl. 15:15-17:00, B2
Session format: the scope of representation learning continued from L10a and introduction to deep generative models 

Before the lecture
Pre-recorded material for lecture L10a.

Discussions 10a Download 10a, 10b Download 10b

After the lecture

Slides Download Slides, Recorded Zoom session 

 

Scope, topics covered

  • Generative models
  • Restricted Boltzmann machines (RBMs), contrastive divergence
  • Gaussian Bernoulli RBMs for continuous data
  • Autoencoders
  • Data representations

 

Reading material:

  • I. Goodfellow et al.: ch.14, 15, 18 (18.1-18.2), 20 (20.1-20.5)

  • tutorials/survey papers, e.g.:
    • Salakhutdinov, R. (2015) Learning deep generative models. Annual Reviews of Statistics and Its Application, 2, p.361–385.
    • Bengio, Y., Courville, A., & Vincent, P. (2013). Representation learning: A review and new perspectives. IEEE transactions on pattern analysis and machine intelligence, 35 (8), p.1798-1828.
    • Bengio, Y. (2009) Learning deep architectures for AI. Foundations and trends® in Machine Learning, 2.1. p.1-127.