CSE 254: Seminar on Learning Algorithms

TuTh 9.30-11 in CSE 2154

Sanjoy Dasgupta
Office hours Th 11-1 in CSE 4138

This quarter the theme of CSE 254 is neurally-inspired unsupervised learning.

The first few lectures will cover basic technical material. Thereafter, each class meeting will consist of student presentations. Each student will present a technical paper (or several papers) in detail. All seminar participants will discuss the paper and the issues raised by it.

Date Presenter
Sep 27 Sanjoy Random projection


Oct 2 Sanjoy Hopfield nets


Oct 4 Sanjoy Markov random fields


Oct 9 Sanjoy Gibbs sampling and restricted Boltzmann machines


Oct 11 Sanjoy Sparse recovery  
Oct 16 Dalin Learning a sparse code for natural images slides
  Huanqiu Efficient auditory coding and Efficient coding of natural sounds slides
Oct 18 Jiayuan Distributed neurally-plausible sparse coding slides
  Shilin Natural image statistics and neural representation slides
Oct 23 Gokce The independent components of natural scenes are edge filters  
  Vijay The neocognitron  
Oct 25 Alankrita Compressed sensing  
  Gaurav More compressed sensing  
Oct 30 Shuang Upper bounds on the capacity of Hopfield nets  
  Sophia Expander codes  
Nov 1 Yaoguang Properties of restricted Boltzmann machines  
  Zhiwei Deep belief nets  
Nov 6 Jongha Mean shift for gradient estimation and mode finding  
  Siva Consistency of mean shift  
Nov 8 Jenny Self-organizing maps  
  Chaitanya, Henry Sparseness and expansion in sensory representations  
Nov 13 Max Memorization and association on a realistic neural model  
  Robi More on Valiant's neuroidal model  
Nov 15 Andrew, Anthony Probabilistic logics and the synthesis of reliable organisms from unreliable components  
  Ivan Highly fault-tolerant parallel computation  
Nov 20 Julaiti Information bottleneck theory of deep learning: part 1 and part 2  
  Fangyi Manifold learning via Isomap: overview and theory  

This is a four unit course in which the work consists of oral presentations.

The procedure for each student presentation is as follows:

Please read, reflect upon, and follow these presentation guidelines, courtesy of Prof Charles Elkan.  Presentations will be evaluated, in a friendly way but with high standards, using this feedback form.

The schedule of presentations will be determined as much as possible on Sep 27.  Here is a preliminary list of papers.

If you want to change your presentation date, please arrange a swap with another student and notify me at least two weeks in advance.