Bio-realistic Neural Network Implementation on Loihi 2 with Izhikevich Neurons

TL;DR

This paper demonstrates implementing a bio-realistic neural network using Izhikevich neurons on Intel's Loihi chip, enabling more diverse neuron dynamics for neuromorphic computing.

Contribution

It introduces a method to implement Izhikevich neuron models on Loihi, expanding the bio-realistic capabilities of neuromorphic hardware.

Findings

Successful integration of Izhikevich neurons on Loihi

Demonstrated simple Go/No-Go task performance

Showed feasibility of custom neuron models on neuromorphic hardware

Abstract

In this paper, we presented a bio-realistic basal ganglia neural network and its integration into Intel's Loihi neuromorphic processor to perform simple Go/No-Go task. To incorporate more bio-realistic and diverse set of neuron dynamics, we used Izhikevich neuron model, implemented as microcode, instead of Leaky-Integrate and Fire (LIF) neuron model that has built-in support on Loihi. This work aims to demonstrate the feasibility of implementing computationally efficient custom neuron models on Loihi for building spiking neural networks (SNNs) that features these custom neurons to realize bio-realistic neural networks.