Unsupervised learning in an ensemble of spiking neural networks mediated by ITDP

Shim, Yoonsik, Philippides, Andy, Staras, Kevin and Husbands, Phil (2016) Unsupervised learning in an ensemble of spiking neural networks mediated by ITDP. PLoS Computational Biology, 12 (10). e1005137. ISSN 1553-734X

[img] PDF - Published Version
Available under License Creative Commons Attribution.

Download (11MB)

Abstract

We propose a biologically plausible architecture for unsupervised ensemble learning in a population of spiking neural network classifiers. A mixture of experts type organisation is shown to be effective, with the individual classifier outputs combined via a gating network whose operation is driven by input timing dependent plasticity (ITDP). The ITDP gating mechanism is based on recent experimental findings. An abstract, analytically tractable model of the ITDP driven ensemble architecture is derived from a logical model based on the probabilities of neural firing events. A detailed analysis of this model provides insights that allow it to be extended into a full, biologically plausible, computational implementation of the architecture which is demonstrated on a visual classification task. The extended model makes use of a style of spiking network, first introduced as a model of cortical microcircuits, that is capable of Bayesian inference, effectively performing expectation maximization. The unsupervised ensemble learning mechanism, based around such spiking expectation maximization (SEM) networks whose combined outputs are mediated by ITDP, is shown to perform the visual classification task well and to generalize to unseen data. The combined ensemble performance is significantly better than that of the individual classifiers, validating the ensemble architecture and learning mechanisms. The properties of the full model are analysed in the light of extensive experiments with the classification task, including an investigation into the influence of different input feature selection schemes and a comparison with a hierarchical STDP based ensemble architecture.

Item Type: Article
Schools and Departments: School of Engineering and Informatics > Informatics
School of Life Sciences > Neuroscience
Research Centres and Groups: Centre for Computational Neuroscience and Robotics
Evolutionary and Adaptive Systems Research Group
Subjects: Q Science > QA Mathematics > QA0076 Computer software
Q Science > QP Physiology > QP0351 Neurophysiology and neuropsychology > QP0361 Nervous system
Depositing User: Phil Husbands
Date Deposited: 21 Oct 2016 11:45
Last Modified: 03 Jul 2017 21:11
URI: http://sro.sussex.ac.uk/id/eprint/64939

View download statistics for this item

📧 Request an update
Project NameSussex Project NumberFunderFunder Ref
INSIGHT-II Darwinian NeurodynamicsG1087EUROPEAN UNION308943