An FPGA-based model suitable for evolution and development of spiking neural networks

Hooman Shayani, PJ Bentley, AM Tyrrell

European Symposium on Artificial Neural Networks, Advances in Computational Intelligence and Learning
2008

Abstract

We propose a digital neuron model suitable for evolving and growing heterogeneous spiking neural networks on FPGAs using a piecewise linear approximation of the Quadratic Integrate and Fire (QIF) model. A network of 161 neurons and 1610 synapses with 4210 times realtime neuron simulation speed was simulated and synthesized for a Virtex-5 chip.

Related Publications

Loading...