[Illinois]: Error Gradient Estimations Due to Parallel Perturbation of Weights

By AbderRahman N Sobh1, Jessica S Johnson1, NanoBio Node1

1. University of Illinois at Urbana-Champaign

This tool trains two-layered networks of sigmoidal units to associate patterns using simultaneous perturbation of weights.

Launch Tool

You must login before you can run this tool.

Version 1.0b - published on 06 Aug 2014

doi:10.4231/D3SQ8QJ4B cite this

Open source: license | download

View All Supporting Documents

    Default Input Simulation



Published on


From Tutorial on Neural Systems Modeling, Chapter 7: This tool trains two-layered, feedforward networks of sigmoidal units on pattern association tasks by estimating the network error gradient using parallel weight pertur­bation, and by updating all network weights simultaneously. This is similar to the one-weight-at-a-time tool pertGradient1By1, except that all weights are perturbed and updated simultaneously. Also the network is not limited to one output unit only.

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, Jessica S Johnson, NanoBio Node (2014), "[Illinois]: Error Gradient Estimations Due to Parallel Perturbation of Weights," https://nanohub.org/resources/pertgradll. (DOI: 10.4231/D3SQ8QJ4B).

    BibTex | EndNote