Spiking neural network with lateral inhibition for reward-based associative learning

In this paper we propose a lateral inhibitory spiking neural network for reward-based associative learning with correlation in spike patterns for conflicting responses. The network has random and sparse connectivity, and we introduce a lateral inhibition via an anatomical constraint and synapse rein...

Full description

Bibliographic Details
Main Authors: Yusoff, Nooraini, Ahmad, Farzana Kabir
Other Authors: Chu, Kiong Loo
Format: Book Section
Published: Springer International Publishing 2014
Subjects:
_version_ 1803627595165597696
author Yusoff, Nooraini
Ahmad, Farzana Kabir
author2 Chu, Kiong Loo
author_facet Chu, Kiong Loo
Yusoff, Nooraini
Ahmad, Farzana Kabir
author_sort Yusoff, Nooraini
collection UUM
description In this paper we propose a lateral inhibitory spiking neural network for reward-based associative learning with correlation in spike patterns for conflicting responses. The network has random and sparse connectivity, and we introduce a lateral inhibition via an anatomical constraint and synapse reinforcement. The spiking dynamic follows the properties of Izhikevich spiking model. The learning involves association of a delayed stimulus pair to a response using reward modulated spike-time dependent plasticity (STDP). The proposed learning scheme has improved our initial work by allowing learning in a more dynamic and competitive environment.
first_indexed 2024-07-04T06:08:33Z
format Book Section
id uum-18762
institution Universiti Utara Malaysia
last_indexed 2024-07-04T06:08:33Z
publishDate 2014
publisher Springer International Publishing
record_format dspace
spelling uum-187622016-10-04T08:08:53Z https://repo.uum.edu.my/id/eprint/18762/ Spiking neural network with lateral inhibition for reward-based associative learning Yusoff, Nooraini Ahmad, Farzana Kabir QA75 Electronic computers. Computer science In this paper we propose a lateral inhibitory spiking neural network for reward-based associative learning with correlation in spike patterns for conflicting responses. The network has random and sparse connectivity, and we introduce a lateral inhibition via an anatomical constraint and synapse reinforcement. The spiking dynamic follows the properties of Izhikevich spiking model. The learning involves association of a delayed stimulus pair to a response using reward modulated spike-time dependent plasticity (STDP). The proposed learning scheme has improved our initial work by allowing learning in a more dynamic and competitive environment. Springer International Publishing Chu, Kiong Loo Keem, Siah Yap Kok, Wai Wong Andrew, Teoh Kaizhu, Huang 2014 Book Section PeerReviewed Yusoff, Nooraini and Ahmad, Farzana Kabir (2014) Spiking neural network with lateral inhibition for reward-based associative learning. In: Neural Information Processing. Lecture Notes in Computer Science, 8834 . Springer International Publishing, Switzerland, pp. 327-334. ISBN 978-3-319-12636-4 http://doi.org/10.1007/978-3-319-12637-1_41 doi:10.1007/978-3-319-12637-1_41 doi:10.1007/978-3-319-12637-1_41
spellingShingle QA75 Electronic computers. Computer science
Yusoff, Nooraini
Ahmad, Farzana Kabir
Spiking neural network with lateral inhibition for reward-based associative learning
title Spiking neural network with lateral inhibition for reward-based associative learning
title_full Spiking neural network with lateral inhibition for reward-based associative learning
title_fullStr Spiking neural network with lateral inhibition for reward-based associative learning
title_full_unstemmed Spiking neural network with lateral inhibition for reward-based associative learning
title_short Spiking neural network with lateral inhibition for reward-based associative learning
title_sort spiking neural network with lateral inhibition for reward based associative learning
topic QA75 Electronic computers. Computer science
work_keys_str_mv AT yusoffnooraini spikingneuralnetworkwithlateralinhibitionforrewardbasedassociativelearning
AT ahmadfarzanakabir spikingneuralnetworkwithlateralinhibitionforrewardbasedassociativelearning