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
 

Adaptation of Spike-Timing-Dependent Plasticity to Unsupervised Learning for Polychronous Wavefront Computing

Thumbnail Image

Files

1-s2.0-S1877050915029762-main.pdf (399.24 KB)

Links to Files

https://www.sciencedirect.com/science/article/pii/S1877050915029762#!

Permanent Link

https://doi.org/10.1016/j.procs.2015.09.146
 http://hdl.handle.net/11603/23051

Collections

UMBC Systems Engineering

Author/Creator

Author/Creator ORCID

Date

2015-10-08

Type of Work

journal articles
Text

Department

Program

Citation of Original Publication

Highland, Fred; Hart, Corey B.; Adaptation of Spike-Timing-Dependent Plasticity to Unsupervised Learning for Polychronous Wavefront Computing; Procedia Computer Science, Volume 61, Pages 314-321, 8 October, 2015; https://doi.org/10.1016/j.procs.2015.09.146

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

Non-Von Neumann computational architectures have lately aroused significant interest as substrates for complex computation. One recent development in this domain is the Polychronous Wavefront Computing (PWC) computational model based on multiple wavefront dynamics. This model is an abstraction and simplification of the artificial neural network paradigm based on temporal and spatial patterns of activity in a pulse propagating media and their interaction with transponders. While this framework is capable of computing basic logical functions and exhibiting interesting dynamic behaviors, methods for unsupervised training of the framework have not been identified. The lack of input weights and the spatio-temporal nature of the PWC framework make direct application of weight adjusting learning methods (e.g., backpropagation) impractical. The paper will describe research into unsupervised learning for PWCs inspired by Spike-Timing-Dependent Plasticity (STDP) methods used with other types of polychronous models. The method is based on adding Leaky Integrate-and-Fire semantics to the PWC framework allowing analysis of activating wavefronts and determination of the optimal location for future stimulation. The transponder's location is then incrementally adjusted to improve its future response. The paper will discuss the learning approach and examine the results of applying the method over a series of stimulations to sample configurations.