Reconfigurable analogue hardware evolution of adaptive spiking neural network controllers

Brian Mc Ginley, Patrick Rocke, Fearghal Morgan, John Maher

Research output: Chapter in Book or Conference Publication/ProceedingConference Publicationpeer-review

5 Citations (Scopus)

Abstract

This paper details the hardware evolution of adaptive Spiking Neural Network (SNN) controllers, implemented on a network of cascaded Field Programmable Analogue Arrays (FPAAs). The fixed architecture, feed forward SNNs are trained using a Genetic Algorithm (GA). An obstacle avoidance simulated robotics controller application is chosen to test the FPAA reconfigurable hardware evolution platform. Evolved behaviours, resulting from FPAA-based SNN controllers, are compared with those obtained using software-based SNN implementations. Results presented indicate the emergence of effective behaviours and adaptation to environmental change.

Original languageEnglish
Title of host publicationGECCO'08
Subtitle of host publicationProceedings of the 10th Annual Conference on Genetic and Evolutionary Computation 2008
Pages289-290
Number of pages2
Publication statusPublished - 2008
Event10th Annual Genetic and Evolutionary Computation Conference, GECCO 2008 - Atlanta, GA, United States
Duration: 12 Jul 200816 Jul 2008

Publication series

NameGECCO'08: Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation 2008

Conference

Conference10th Annual Genetic and Evolutionary Computation Conference, GECCO 2008
Country/TerritoryUnited States
CityAtlanta, GA
Period12/07/0816/07/08

Keywords

  • Analogue neural networks
  • FPAA hardware evolution
  • Spiking neural networks

Fingerprint

Dive into the research topics of 'Reconfigurable analogue hardware evolution of adaptive spiking neural network controllers'. Together they form a unique fingerprint.

Cite this