This is the QA environment of the MD-SOAR platform. It is for TESTING PURPOSES ONLY. Navigate to https://mdsoar.org to access the latest open access research from MD-SOAR institutions.
QA Environment
 

Implementing Multilayer Neural Network Behavior Using Polychronous Wavefront Computation

Thumbnail Image

Files

1-s2.0-S1877050916324802-main.pdf (510.91 KB)

Links to Files

https://www.sciencedirect.com/science/article/pii/S1877050916324802#!

Permanent Link

https://doi.org/10.1016/j.procs.2016.09.307
 http://hdl.handle.net/11603/23049

Collections

UMBC Systems Engineering
UMBC Faculty Collection

Author/Creator

Author/Creator ORCID

Date

2016-10-30

Type of Work

journal articles
Text

Department

Program

Citation of Original Publication

Highland, Fred; Hart, Corey; Implementing Multilayer Neural Network Behavior Using Polychronous Wavefront Computation; Procedia Computer Science, Volume 95, Pages 159-167, 30 October, 2016; https://doi.org/10.1016/j.procs.2016.09.307

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0)

Subjects

Abstract

Polychronous Wavefront Computation (PWC) is an abstraction of spiking neural networks that provides a potentially practical model for implementing neuromorphic computing systems. While it's has been shown to exhibit some basic computational capabilities, its use in complex neuro-computational models remains to be explored. The paper presents a model and approach for configuring PWC transponders to implement multilayer neural network behavior to provide a basis for more complex applications of the technology. The model uses a set of input transponders representing pattern features to stimulate hidden layer transponders that combine features and trigger output layer transponders to identify patterns. The input layer transponder geometry is selected to create wavefront intersections for all relevant feature combinations. Hidden layer transponders are positioned by solving the intersection of the circles equations defined by sets of input transponders. Output layer transponders are defined to collect complete sets of features for recognition based on the hidden layer transponder geometry. The approach uses the intersections of three wavefronts to maximize transponder selectivity and increase information density. The concept is experimentally demonstrated and analyzed with a 7-segment display digit recognition application which provides a simple but representative example of more complex pattern recognition problems.