eprintid: 10080543 rev_number: 32 eprint_status: archive userid: 608 dir: disk0/10/08/05/43 datestamp: 2019-08-28 14:24:36 lastmod: 2021-01-17 07:10:07 status_changed: 2020-06-17 18:16:44 type: proceedings_section metadata_visibility: show creators_name: Kozdon, K creators_name: Bentley, P title: Normalisation of Weights and Firing Rates in Spiking Neural Networks with Spike-Timing-Dependent Plasticity ispublished: pub divisions: UCL divisions: A01 divisions: B04 divisions: C05 divisions: F48 keywords: spiking neural networks, neural networks, AI note: This version is the version of record. For information on re-use, please refer to the publisher’s terms and conditions. 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. date: 2019-07-29 date_type: published publisher: Developmental Neural Networks official_url: https://www.irit.fr/devonn/files/alife2019-kozdon.pdf oa_status: green full_text_type: pub language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1685422 lyricists_name: Bentley, Peter lyricists_name: Kozdon, Katarzyna lyricists_id: PJBEN84 lyricists_id: KOZDO75 actors_name: Kozdon, Katarzyna actors_id: KOZDO75 actors_role: owner full_text_status: public publication: The developmental neural networks workshop place_of_pub: Newcastle, United Kingdom event_title: The 2019 Conference on Artificial Life event_location: Newcastle, United Kingdom event_dates: 29 July 2019 - 02 August 2019 institution: the Artificial Life Conference (Life) book_title: Proceedings of the 2019 Conference on Artificial Life citation: 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 document_url: https://discovery.ucl.ac.uk/id/eprint/10080543/7/Kozdon_Normalisation%20of%20Weights%20and%20Firing%20Rates%20in%20Spiking%20Neural%20Networks%20with%20Spike-Timing-Dependent%20Plasticity_AAM.pdf