Skip to main navigation Skip to search Skip to main content

Performance optimization of echo state networks through principal neuron reinforcement

  • State University of New York Binghamton University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

7 Scopus citations

Abstract

The nature of Echo State Networks (ESN) allows this class of recurrent neural network to model dynamic systems with relatively low training requirements. However, the randomly initialized reservoir of the ESN brings about complications with choosing starting parameters. A neuroplasticity-inspired algorithm was proposed in this study to alter the strength of internal synapses within the reservoir towards the goal of optimizing the neuronal dynamics of the ESN pertaining to the specific problem to be solved. It was found that the algorithm was able to modify the reservoir connections so that after retraining, the performance of different reservoir sizes was comparable despite being vastly different before. It was also found that by applying the proposed algorithm, the difficulty in the choice of initialization connectivity and reservoir size can be greatly reduced.

Original languageEnglish
Title of host publication2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1717-1723
Number of pages7
ISBN (Electronic)9781509061815
DOIs
StatePublished - Jun 30 2017
Event2017 International Joint Conference on Neural Networks, IJCNN 2017 - Anchorage, United States
Duration: May 14 2017May 19 2017

Publication series

NameProceedings of the International Joint Conference on Neural Networks
Volume2017-May

Conference

Conference2017 International Joint Conference on Neural Networks, IJCNN 2017
Country/TerritoryUnited States
CityAnchorage
Period05/14/1705/19/17

Keywords

  • Echo state network
  • Hebbian learning
  • Neuroplasticity
  • Principal neuron
  • Reservoir computing

Fingerprint

Dive into the research topics of 'Performance optimization of echo state networks through principal neuron reinforcement'. Together they form a unique fingerprint.

Cite this