TY - GEN
T1 - Reconfigurable analogue hardware evolution of adaptive spiking neural network controllers
AU - Ginley, Brian Mc
AU - Rocke, Patrick
AU - Morgan, Fearghal
AU - Maher, John
PY - 2008
Y1 - 2008
N2 - 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.
AB - 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.
KW - Analogue neural networks
KW - FPAA hardware evolution
KW - Spiking neural networks
UR - https://www.scopus.com/pages/publications/57349156957
M3 - Conference Publication
AN - SCOPUS:57349156957
SN - 9781605581309
T3 - GECCO'08: Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation 2008
SP - 289
EP - 290
BT - GECCO'08
T2 - 10th Annual Genetic and Evolutionary Computation Conference, GECCO 2008
Y2 - 12 July 2008 through 16 July 2008
ER -