TuTh 3.30-5 in CSE 2154
Office hours TBA in EBU3B 4138
This quarter the theme of CSE 254 is deep learning.
Prerequisite: CSE 250AB.
The first couple of lectures will be an overview of basic material. Thereafter, in each class meeting, a student will give a talk lasting about 60 minutes presenting a technical paper (or several papers) in detail. In questions during the talk, and in the final 20 minutes, all seminar participants will discuss the paper and the issues raised by it.
|Jan 12||Sanjoy||Hopfield nets||
|Jan 17||Sanjoy||Markov random fields, Gibbs sampling, simulated annealing||
|Jan 19||Sanjoy||Deep belief nets as autoencoders and classifiers||
|Jan 24||Brian||Task-driven dictionary learning|
|Jan 26||Vicente||A quantitative theory of immediate visual recognition|
|Jan 31||Emanuele||Convolutional deep belief networks|
|Feb 2||Nakul||Restricted Boltzmann machines: learning, and hardness of inference|
|Feb 7||Craig||The independent components of natural scenes are edge filters|
|Feb 9||No class: ITA conference at UCSD||
|Feb 14||Janani||Deep learning via semi-supervised embedding|
|Feb 16||Stefanos||A unified architecture for natural language processing|
|Feb 21||Hourieh||An analysis of single-layer networks in unsupervised feature learning|
|Feb 23||Ozgur||Emergence of simple-cell receptive properties by learning a sparse code for natural images|
|Feb 28||Matus||Representation power of neural networks: Barron, Cybenko, Kolmogorov|
|Mar 1||Frederic||Reinforcement learning on slow features of high-dimensional input streams||
|Mar 6||Dibyendu, Sreeparna||Learning deep energy models and What is the best multistage architecture for object recognition?|
|Mar 8||No class: Sanjoy out of town||
|Mar 13||Bryan||Inference of sparse combinatorial-control networks|
|Mar 15||Qiushi||Weighted sums of random kitchen sinks|
This is a four unit course in which the work consists of oral presentations.
The procedure for each student presentation is as follows:
The schedule of presentations will be determined as much as possible on Tuesday Jan 10. 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.