Reconfigurable analogue hardware evolution of adaptive spiking neural network controllers

Authors:
Brian McGinley;Patrick Rocke;Fearghal Morgan;John Maher
Affiliations:
National University of Ireland, Galway, Galway, Ireland;National University of Ireland, Galway, Galway, Ireland;National University of Ireland, Galway, Galway, Ireland;National University of Ireland, Galway, Galway, Ireland
Venue:
Proceedings of the 10th annual conference on Genetic and evolutionary computation
Year:
2008

Citing 4
Cited 0

Hardware Evolution of Analog Circuits for In-situ Robotic Fault-Recovery

EH '05 Proceedings of the 2005 NASA/DoD Conference on Evolvable Hardware
Platform for Intrinsic Evolution of Analogue Neural Networks

RECONFIG '05 Proceedings of the 2005 International Conference on Reconfigurable Computing and FPGAs (ReConFig'05) on Reconfigurable Computing and FPGAs
Intrinsic Hardware Evolution of Neural Networks in Reconfigurable Analogue and Digital Devices

FCCM '06 Proceedings of the 14th Annual IEEE Symposium on Field-Programmable Custom Computing Machines
GRACE: generative robust analog circuit exploration

EuroGP'06 Proceedings of the 2006 international conference on Applications of Evolutionary Computing

Quantified Score

Hi-index	0.00

Visualization

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.