Lecture 21 (take two), April 2nd, 2015: Recurrent Neural Networks

We will again attempt to discuss Recurrent Neural Networks. If we are unable to meet, please continue reading the material and posting discussion points. I’ll try to answer questions directly and replies.

Please study the following additional material in preparation for class:

Other relevant material:

Advertisements

Lecture 21, March 30th, 2015: Recurrent Neural Networks

In this lecture we will discuss Recurrent Neural Networks.

Please study the following material in preparation for class:

Other relevant material:

Lecture 20, March 26th, 2015: The Variational Autoencoder

In this lecture we will discuss Variational Autoencoders.

Please study the following material in preparation for class:

Other relevant material:

Lecture 18, March 19th, 2015: Deep Belief Networks

In this lecture we will continue our discussion of probabilistic undirected graphical models with the Deep Belief Network. The material is that listed from the last lecture plus the material below.

Please study the following material in preparation for the class:

Other relevant material:

Lecture 17, March 16th, 2015: RBMs continued and Deep Belief Nets

In this lecture we will continue our discussion of probabilistic undirected graphical models such as the Restricted Boltzmann Machine and moving on to the Deep Belief Network. We will also review the quiz from last Monday.

Please study the following material in preparation for the class:

  • Lecture 7 (esp. 7.7 to 7.9) of Hugo Larochelle’s course on Neural Networks.
  • Chapter 21 (sec. 21.3) of the Deep Learning Textbook on deep generative models

Other relevant material:

  •  Lectures 14 of Geoff Hinton’s cousera course on Neural Networks.

Lecture 16, March 12th, 2015: Restricted Boltzmann Machines

In this lecture we will begin our discussion of probabilistic undirected graphical models. In particular, we will study the Restricted Boltzmann Machine.

Please study the following material in preparation for the class:

  • Lecture 5 (5.1 to 5.8) of Hugo Larochelle’s course on Neural Networks.
  • Chapter 9 of the Deep Learning Textbook (important background on probabilistic models).
  • Chapter 15 (sec. 15.2) of the Deep Learning Textbook (approximate maximum likelihood training)
  • Chapter 21 (sec. 21.2) of the Deep Learning Textbook on deep generative models

Other relevant material:

  •  Lectures 11 and 12 ( especially 11d-11e and 12a-12e ) of Geoff Hinton’s cousera course on Neural Networks.