You must login before you can run this tool.
[Illinois]: Error Gradient Estimations Due to Parallel Perturbation of Weights
This tool trains two-layered networks of sigmoidal units to associate patterns using simultaneous perturbation of weights.
Category
Published on
Abstract
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