A Practical Guide to Tuning Spiking Neuronal Dynamics

TL;DR

This paper provides a practical guide to tuning spiking neural networks by examining fundamental neuronal units, hyperparameters, and design choices affecting network dynamics.

Contribution

It offers detailed insights into how to effectively tune LIF and RAF neurons and design SNNs for desired behaviors, filling a gap in practical guidance.

Findings

Hyperparameters significantly influence neuron behavior

Input encoding impacts network dynamics

Design choices affect excitatory-inhibitory balance

Abstract

In this work, we examine fundamental elements of spiking neural networks (SNNs) as well as how to tune them. Concretely, we focus on two different foundational neuronal units utilized in SNNs -- the leaky integrate-and-fire (LIF) and the resonate-and-fire (RAF) neuron. We explore key equations and how hyperparameter values affect behavior. Beyond hyperparameters, we discuss other important design elements of SNNs -- the choice of input encoding and the setup for excitatory-inhibitory populations -- and how these impact LIF and RAF dynamics.