Adapting unconstrained spiking neural networks to explore the effects of time discretization on network properties

The effects of time-discretization on spike-based backpropagation as opposed to membrane-potential backpropagation

Bachelor thesis (2024)

Authors

L.I. Chalakova Electrical Engineering, Mathematics and Computer Science

Contributors

N. Tömen Pattern Recognition and Bioinformatics - EEMCS (mentor)
A. Micheli Pattern Recognition and Bioinformatics - EEMCS (graduation committee member)
Faculty
Electrical Engineering, Mathematics and Computer Science
More Info
expand_more

Published Date

25-06-2024

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Faculty

Electrical Engineering, Mathematics and Computer Science

Abstract

The promise of Artificial Neural Networks has lead to their immense usage intertwined with concerns over energy consumption. This has led to development of alternatives, such as Spiking Neural Networks (SNNs), which allows their implementation on neuromorphic hardware. In effect, the network must be time discretized. SNNs learn through backpropagation, similarly to ANNs, where two main methods exist: spike-based backpropagation and backpropagation through time. This study investigates and compares the effect of varying timesteps on the convergence rate of BATS, an example of spikebased backpropagation, and of SLAYER - an example of backpropagation through time on the NMNIST and MNIST dataset. The results conclude that BATS withstands growing timestep sizes. Although SLAYER maintains a good performance for small timestep sizes, it seems to self-destruct as they grow.