[Illinois]: Error Gradient Estimations Due to Perturbation of One Weight at a Time

By AbderRahman N Sobh

University of Illinois at Urbana-Champaign

This tool trains two-layered networks of sigmoidal units to associate patterns using perturbation of one weight at a time.

Launch Tool

This tool version is unpublished and cannot be run. If you would like to have this version staged, you can put a request through HUB Support.

Archive Version 1.0a
Published on 09 Jul 2013 All versions

doi:10.4231/D3PZ51M3T cite this

Category

Tools

Published on

Abstract

From Tutorial on Neural Systems Modeling, Chapter 7, pg. 242: This tool trains two-layered, feedforward networks having multiple input units, but only one output unit, to associate patterns using gradient estimation through perturbation of one weight at a time.

Sponsored by

NanoBio Node, University of Illinois Champaign-Urbana

Cite this work

Researchers should cite this work as follows:

  • Tutorial on Neural Systems Modeling, Copyright 2010 Sinauer Associates Inc. Author: Thomas J. Anastasio
  • AbderRahman N Sobh (2014), "[Illinois]: Error Gradient Estimations Due to Perturbation of One Weight at a Time," https://nanohub.org/resources/pertgrad1by1. (DOI: 10.21981/D3PZ51M3T).

    BibTex | EndNote

Tags