Fil, Jakub, Chu, Dominique (2020) Minimal spiking neuron for solving multi-label classification tasks. Neural Computation, 32 (7). pp. 1408-1429. ISSN 0899-7667. E-ISSN 1530-888X. (doi:10.1162/neco_a_01290) (KAR id:80477)
PDF
Publisher pdf
Language: English |
|
Download this file (PDF/1MB) |
|
Request a format suitable for use with assistive technology e.g. a screenreader | |
Official URL: https://doi.org/10.1162/neco_a_01290 |
Abstract
The Multi-Spike Tempotron (MST) is a powerful single spiking neuron model that can solve complex supervised classification tasks. While powerful, it is also internally complex, computationally expensive to evaluate, and not suitable for neuromorphic hardware. Here we aim to understand whether it is possible to simplify the MST model, while retaining its ability to learn and to process information. To this end, we introduce a family of Generalised Neuron Models (GNM) which are a special case of the Spike Response Model and much simpler and cheaper to simulate than the MST. We find that over a wide range of parameters the GNM can learn at least as well as the MST. We identify the temporal autocorrelation of the membrane potential as the single most important ingredient of the GNM which enables it to classify multiple spatio-temporal patterns. We also interpret the GNM as a chemical system, thus conceptually bridging computation by neural networks with molecular information processing. We conclude the paper by proposing alternative training approaches for the GNM including error trace learning and error backpropagation.
Item Type: | Article |
---|---|
DOI/Identification number: | 10.1162/neco_a_01290 |
Uncontrolled keywords: | Spiking neural networks, aggregate label learning, supervised learning, multi-spike tempotron, chemical reaction networks |
Divisions: | Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing |
Depositing User: | Jakub Fil |
Date Deposited: | 18 Aug 2020 10:49 UTC |
Last Modified: | 05 Nov 2024 12:46 UTC |
Resource URI: | https://kar.kent.ac.uk/id/eprint/80477 (The current URI for this page, for reference purposes) |
- Link to SensusAccess
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):