Chu, Dominique (2023) Information theoretical properties of a spiking neuron trained with Hebbian and STDP learning rules. Natural Computing, . ISSN 1567-7818. E-ISSN 1572-9796. (doi:10.1007/s11047-022-09939-6) (KAR id:99451)
PDF
Publisher pdf
Language: English
This work is licensed under a Creative Commons Attribution 4.0 International License.
|
|
Download this file (PDF/2MB) |
Preview |
Request a format suitable for use with assistive technology e.g. a screenreader | |
Official URL: https://doi.org/10.1007/s11047-022-09939-6 |
Abstract
Using formal methods complemented by large-scale simulations we investigate information theoretical properties of spiking neurons trained using Hebbian and STDP learning rules. It is shown that weight space contains meta-stable states, which are points where the average weight change under the learning rule vanishes. These points may capture the random walker transiently. The dwell time in the vicinity of the meta-stable state is either quasi-infinite or very short and depends on the level of noise in the system. Moreover, important information theoretic quantities, such as the amount of information the neuron transmits are determined by the meta-stable state. While the Hebbian learning rule reliably leads to meta-stable states, the STDP rule tends to be unstable in the sense that for most choices of hyper-parameters the weights are not captured by meta-stable states, except for a restricted set of choices. It emerges that stochastic fluctuations play an important role in determining which meta-stable state the neuron takes. To understand this, we model the trajectory of the neuron through weight space as an inhomogeneous Markovian random walk, where the transition probabilities between states are determined by the statistics of the input signal.
Item Type: | Article |
---|---|
DOI/Identification number: | 10.1007/s11047-022-09939-6 |
Additional information: | For the purpose of open access, the author has applied a CC BY public copyright licence to any Author Accepted Manuscript version arising from this submission. |
Uncontrolled keywords: | Hebbian learning, Spike-timing dependent plasticity, Stochastic systems, Random walk |
Subjects: | Q Science > Q Science (General) > Q335 Artificial intelligence |
Divisions: | Divisions > Division of Computing, Engineering and Mathematical Sciences > School of Computing |
Funders: | Engineering and Physical Sciences Research Council (https://ror.org/0439y7842) |
Depositing User: | Dominique Chu |
Date Deposited: | 09 Jan 2023 11:08 UTC |
Last Modified: | 27 Feb 2024 10:56 UTC |
Resource URI: | https://kar.kent.ac.uk/id/eprint/99451 (The current URI for this page, for reference purposes) |
- Link to SensusAccess
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):