[Illinois]: Sigmoidal unit training with the delta rule

By Lisa Sproat

University of Illinois at Urbana-Champaign

Uses the delta rule to train a single sigmoidal unit with feedback to simulate the responses of neurons in the parabigeminal nucleus

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This tool version is unpublished and cannot be run.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 19 Aug 2013 All versions

doi:10.4231/D3S756K2N cite this

Category

Tools

Published on

Abstract

This tool uses the delta rule to train a single sigmoidal unit with feedback to simulate the responses of neurons in the parabigeminal nucleus.

FIGURE 12.19 is a model of a single neuron in the parabigeminal nucleus (PBN) The model PBN neuron receives input from itself, from a bias unit, and from the superficial and deep layers of the superior colliculus (SSC and DSC, respectively). The SSC is represented as an array of 161 input units (of which only five are shown), while the DSC and bias are single input units.

This tool is built from the MATLAB scripts for Tutorial on Neural Systems Modeling by Thomas J. Anastasio.

Sponsored by

References

Anastasio, T. J. (2009). Tutorial on Neural Systems Modeling. Sinauer Associates, Incorporated.

Cite this work

Researchers should cite this work as follows:

  • Lisa Sproat (2015), "[Illinois]: Sigmoidal unit training with the delta rule," http://nanohub.org/resources/pbndeltarule. (DOI: 10.21981/D3S756K2N).

    BibTex | EndNote

Tags