English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Learning in the Context of Change-based Inference

Moazzezi, R., & Dayan, P. (2008). Learning in the Context of Change-based Inference. Poster presented at Workshop Local-Area Systems & Theoretical Neuroscience Day (LSTN 2008), London, UK.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0003-7147-E Version Permalink: http://hdl.handle.net/21.11116/0000-0003-7148-D
Genre: Poster

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Moazzezi, R, Author
Dayan, P1, Author              
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: We have recently investigated a new way of conceptualizing the inferential capacities of non-linear re-current networks in terms of the change in a statistic of the population activity over the time since a stimulus is presented. Evaluating change allows inferences to be fast, relatively insensitive to noise, and, in suitable cases, invariant to irrelevant dimensions of the stimulus. We proved the technique in the context of the bisection task, which is a popular psychophysical testbed for visual hyperacuity, using recurrent weights whose values were determined by hand. One central observation was that a wide range of structurally different sets of recurrent weights supports near-optimal behaviour. This suggests that a learning algorithm could work well. Here, we show the power of using backpropagation-through-time algorithm (BPTT) to learn weight matrices to solve the task, where we evaluated the change in the location of the centre of mass (in visual space) of the network over the course of one, discrete, iteration. We directly imposed the obvious prior constraint of translation invariance. BPTT was readily able to find many appropriate sets of recurrent weights that perform near-optimally; different initial conditions lead to different weights. This breadth demonstrates the benefits of an appropriate computational representation of the task. We are presently analyzing how the network performs this inference in a highly non-linear regime, far from equilibrium.

Details

show
hide
Language(s):
 Dates: 2008-07
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: Workshop Local-Area Systems & Theoretical Neuroscience Day (LSTN 2008)
Place of Event: London, UK
Start-/End Date: 2008-07-08

Legal Case

show

Project information

show

Source 1

show
hide
Title: Workshop Local-Area Systems & Theoretical Neuroscience Day (LSTN 2008)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: 51 Start / End Page: 37 Identifier: -