Bayesian Nonparametric Methods: Hope or Hype?

Discussion of Erik Sudderth's talk: NPB Hype or Hope?

author: Yann LeCun, Computer Science Department, New York University
published: Jan. 24, 2012, recorded: December 2011, views: 427

Slides

Slides
0:00	NPB Hype or Hope?
0:01	Hierachical Feed-Back Processing
1:45	Does the Brain Use NPB?
3:16	Hierarchical Feed-Forward Processing
4:18	The dominant model for object recognition
5:21	The dominant model is (indirectly inspired by (half of) neuroscience
5:45	Hierarchical Processing
6:43	Feed-Forward Feed-Back Architecture for Learning
6:46	Predictive Sparse Decomposition (PSD)
7:35	Using PSD to Train a Hierarchy of Features - 1
8:08	Using PSD to Train a Hierarchy of Features - 2
8:29	Pedestrian Detection (INRIA Dataset)
9:47	Multi-Scale ConvNet: Application to Full-Scene Labeling
9:48	Labeling Every Pixel in the Image
10:29	Scene Parsing / Labeling: ConvNet Architecture
10:48	Scene Parsing / Labeling: System Architecture
11:31	Scene Parsing / Labeling: Performance
13:21	Scene Parsing / Labeling: SIFT Flow dataset - 1
13:39	Scene Parsing / Labeling: SIFT Flow dataset - 2
13:40	Scene Parsing / Labeling - 1
13:42	Scene Parsing / Labeling - 2
13:43	Hardware Implementations in FPGAs and chips
13:44	NewFlow: Architecture
14:16	NewFlow: Latest Hardware

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.

Lecture popularity: You need to login to cast your vote.