Search    
Find    

2010 Rockwood Memorial Lecture

 

Geoffrey Hinton


When:
4:00PM, Wednesday, March 10, 2010


Where:
Institute of the Americas, Weaver Conference Center, UC San Diego,


Title: "Deep learning with multiplicative interactions”


Abstract:
Deep networks can be learned efficiently from unlabeled data. The layers of representation are learned one at a time using a simple learning module that has only one layer of latent variables. The values of the latent variables of one module form the data for training the next module. The most commonly used modules are Restricted Boltzmann Machines or autoencoders with a sparsity penalty on the hidden activities. Although deep networks have been quite successful for tasks such as object recognition, information retrieval, and modeling motion capture data, the simple learning modules do not have multiplicative interactions which are very useful for some types of data.
The talk will show how a third-order energy function can be factorized to yield a simple learning module that retains advantageous properties of a Restricted Boltzmann Machine such as very simple exact inference and a very simple learning rule based on pair-wise statistics. The new module has a structure that is very similar to the simple cell/complex cell hierarchy that is found in visual cortex. The multiplicative interactions are useful for modeling images, image transformations, and different styles of human walking.


Host: Terry Sejnowski

 

 


Resources:


MB

Faculty Spotlight

Tzyy-Ping Jung
Elevated to IEEE Fellow for contributions to blind source separation for biomedical applications.

...more info


Staff Spotlight

INC's First Annual Hike N' Lunch Event
INC Staff at the Torrey Pines Glider Port.

...see more