FPGA based platform for spiking neural network

Abstract

Neuromorphic engineers are studying the nervous system and trying to emulate its function and organization in their computational and robotics systems. They are hoping to match the human brain in vision, hearing, pattern recognition and learning tasks. Our goal is to create Field Programmeble Gate Array (FPGA) platforms of large-scale spiking neural networks to allow the testing of certain hypotheses related to neuroscience theories. Virtualization is also very important concept for spiking neural network. In this work, we also analyze effect of virtualization on performance and performance/price of spiking neural network. We implement general purpose spiking neural network platform using Spartan 3E FPGA and observe performance and performance/price tradeoffs.