Why Spiking Neural Networks Are Efficient: A Theorem

Beer, Michael ORCID: 0000-0002-0611-0345, Urenda, Julio, Kosheleva, Olga and Kreinovich, Vladik (2020) Why Spiking Neural Networks Are Efficient: A Theorem. .

Text
spikesa.pdf - Author Accepted Manuscript
Download (263kB) | Preview

Official URL: http://dx.doi.org/10.1007/978-3-030-50146-4_5

Abstract

Current artificial neural networks are very successful in many machine learning applications, but in some cases they still lag behind human abilities. To improve their performance, a natural idea is to simulate features of biological neurons which are not yet implemented in machine learning. One of such features is the fact that in biological neural networks, signals are represented by a train of spikes. Researchers have tried adding this spikiness to machine learning and indeed got very good results, especially when processing time series (and, more generally, spatio-temporal data). In this paper, we provide a possible theoretical explanation for this empirical success.

Item Type:	Conference or Workshop Item (Unspecified)
Uncontrolled Keywords:	Neurosciences
Depositing User:	Symplectic Admin
Date Deposited:	21 Jul 2020 07:59
Last Modified:	15 Mar 2024 05:27
DOI:	10.1007/978-3-030-50146-4_5
Related URLs:	Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3094350