Biologically Inspired Spiking Neurons : Piecewise Linear Models and Digital Implementation

TL;DR

This paper introduces piecewise linear spiking neuron models inspired by biology, demonstrating their efficient digital implementation on FPGA, enabling scalable neuromorphic hardware with accurate neural behaviors for applications like character recognition.

Contribution

The paper proposes novel piecewise linear spiking neuron models suitable for digital hardware, with demonstrated high performance and low cost for large-scale neuromorphic systems.

Findings

Models accurately reproduce biological neuron behaviors

Hardware implementation on FPGA is efficient and cost-effective

Successful application in character recognition task

Abstract

There has been a strong push recently to examine biological scale simulations of neuromorphic algorithms to achieve stronger inference capabilities. This paper presents a set of piecewise linear spiking neuron models, which can reproduce different behaviors, similar to the biological neuron, both for a single neuron as well as a network of neurons. The proposed models are investigated, in terms of digital implementation feasibility and costs, targeting large scale hardware implementation. Hardware synthesis and physical implementations on FPGA show that the proposed models can produce precise neural behaviors with higher performance and considerably lower implementation costs compared with the original model. Accordingly, a compact structure of the models which can be trained with supervised and unsupervised learning algorithms has been developed. Using this structure and based on a spike rate coding, a character recognition case study has been implemented and tested.