Yusoff, Nooraini and Ibrahim, Mohammed Fadhil (2018) Spatio-temporal event association using reward-modulated spike-time-dependent plasticity. Information Sciences, 451-45. pp. 143-160. ISSN 00200255

Full text not available from this repository. (Request a copy)

Abstract

For goal-directed learning in spiking neural networks, target spike templates are usually required.Optimal performance is achieved by minimising the error between the desired and output spike timings.However, in some dynamic environments, a set of learning targets with precise encoding is not always available.For this study, we associate a pair of spatio-temporal events with a target response using a reinforcement learning approach.The learning is implemented in a recurrent spiking neural network using reward-modulated spike-time-dependent plasticity.The learning protocol is simple and inspired by a behavioural experiment from a neuropsychology study.For a goal-directed application, learning does not require a target spike template.In this study, convergence is measured by synchronicity of activities in associated neuronal groups.As a result of learning, a network is able to associate a pair of events with a temporal delay in a dynamic setting. The results demonstrate that the algorithm can also learn temporal sequence detection.Learning has also been tested in face-voice association using real biometric data.The loose dependency between the model's anatomical properties and functionalities could offer a wide range of applications, especially in complex learning environments.

Item Type:	Article
Uncontrolled Keywords:	Spiking neural networks Associative learning Spike-time-dependent plasticity Reward-based learningSpatio-temporal events
Subjects:	L Education > LB Theory and practice of education
Divisions:	School of Education & Modern Languages
Depositing User:	Mrs. Norazmilah Yaakub
Date Deposited:	04 Jul 2018 01:51
Last Modified:	04 Jul 2018 01:51
URI:	https://repo.uum.edu.my/id/eprint/24363

Actions (login required)

View Item