Learning in neural networks

Petruț Antoniu Bogdan, Garibaldi Pineda García, Michael Hopkins, Edward Jones, James Courtney Knight, Adam Perrett

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

This chapter is concerned with the motivation, design and implementation behind mimicking biological learning rules with a focus on, you guessed it, SpiNNaker. It starts by presenting Spike-timing-dependent plasticity (STDP) operating in an unsupervised fashion based on relative spike times of the pre- and post-synaptic neurons or based on the sub-threshold membrane potential. This is followed by a model of STDP modulated by the presence of an additional signal and operating on eligibility traces. Longer-term mechanisms in the form of structural plasticity, involving the rewiring of connections between the neurons, and (very long-term) neuroevolution close out the chapter.
Original languageEnglish
Title of host publicationSpiNNaker
Subtitle of host publicationa spiking neural network architecture
EditorsSteve Furber, Petruț Antoniu Bogdan
Place of PublicationBoston-Delft
PublisherNow Publishers Inc
Chapter7
Pages209-265
Number of pages57
ISBN (Electronic) 9781680836530
ISBN (Print)9781680835960
DOIs
Publication statusPublished - 31 Mar 2020

Fingerprint

Dive into the research topics of 'Learning in neural networks'. Together they form a unique fingerprint.

Cite this