UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Normalisation of Weights and Firing Rates in Spiking Neural Networks with Spike-Timing-Dependent Plasticity

Kozdon, K; Bentley, P; (2019) Normalisation of Weights and Firing Rates in Spiking Neural Networks with Spike-Timing-Dependent Plasticity. In: Proceedings of the 2019 Conference on Artificial Life. Developmental Neural Networks: Newcastle, United Kingdom. Green open access

[thumbnail of Kozdon_Normalisation of Weights and Firing Rates in Spiking Neural Networks with Spike-Timing-Dependent Plasticity_AAM.pdf]
Preview
Text
Kozdon_Normalisation of Weights and Firing Rates in Spiking Neural Networks with Spike-Timing-Dependent Plasticity_AAM.pdf - Accepted Version

Download (210kB) | Preview

Abstract

Maintaining the ability to fire sparsely is crucial for infor- mation encoding in neural networks. Additionally, spiking homeostasis is vital for spiking neural networks with chang- ing numbers of weights and neurons. We discuss a range of network stabilisation approaches, inspired by homeostatic synaptic plasticity mechanisms reported in the brain. These include weight scaling, and weight change as a function of the network’s spiking activity. We tested normalisation of the sum of weights for all neurons, and by neuron type. We ex- amined how this approach affects firing rate and performance on clustering of time-series data in the form of moving geo- metric shapes. We found that neuron type-specific normali- sation is a promising approach for preventing weight drift in spiking neural networks, thus enabling longer training cycles. It can be adapted for networks with architectural plasticity.

Type: Proceedings paper
Title: Normalisation of Weights and Firing Rates in Spiking Neural Networks with Spike-Timing-Dependent Plasticity
Event: The 2019 Conference on Artificial Life
Location: Newcastle, United Kingdom
Dates: 29 July 2019 - 02 August 2019
Open access status: An open access version is available from UCL Discovery
Publisher version: https://www.irit.fr/devonn/files/alife2019-kozdon....
Language: English
Additional information: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions.
Keywords: spiking neural networks, neural networks, AI
UCL classification: UCL
UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery.ucl.ac.uk/id/eprint/10080543
Downloads since deposit
21Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item