Hardware Implementation of a Bio-plausible Neuron Model for Evolution and Growth of Spiking Neural Networks on FPGA
Authors:
- Hooman ShayaniHSHooman Shayani
- Peter J. BentleyPBPeter J. Bentley
- Andy M. TyrrellATAndy M. Tyrrell
- 1 June 2008
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 236-243
Abstract
We propose a digital neuron model suitable for evolving and growing heterogeneous spiking neural networks on FPGAs by introducing a novel flexible dendrite architecture and the new PLAQIF (piecewise-linear approximation of quadratic integrate and fire) soma model. A network of 161 neurons and 1610 synapses was simulated, implemented, and verified on a Virtex-5 chip with 4210 times real-time speed with 1 ms resolution. The parametric flexibility of the soma model was shown through a set of experiments.Keywords
This publication has 24 references indexed in Scilit:
- The POEtic Electronic Tissue and Its Role in the Emulation of Large-Scale Biologically Inspired Spiking Neural Networks ModelsComplexus, 2006
- Evolution of spiking neural circuits in autonomous mobile robotsInternational Journal of Intelligent Systems, 2006
- Real-Time Neuroevolution in the NERO Video GameIEEE Transactions on Evolutionary Computation, 2005
- A regenerating spiking neural networkNeural Networks, 2005
- Which Model to Use for Cortical Spiking Neurons?IEEE Transactions on Neural Networks, 2004
- Simple model of spiking neuronsIEEE Transactions on Neural Networks, 2003
- Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on PerturbationsNeural Computation, 2002
- Evolving Neural Networks through Augmenting TopologiesEvolutionary Computation, 2002
- Evolving artificial neural networksProceedings of the IEEE, 1999
- No free lunch theorems for optimizationIEEE Transactions on Evolutionary Computation, 1997