University of Sussex
Browse
SpikingEnsemblePCB-2016.pdf (10.72 MB)

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

Download (10.72 MB)
journal contribution
posted on 2023-06-09, 03:39 authored by Yoonsik Shim, Andy PhilippidesAndy Philippides, Kevin StarasKevin Staras, Phil HusbandsPhil Husbands
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.

Funding

INSIGHT-II Darwinian Neurodynamics; G1087; EUROPEAN UNION; 308943

History

Publication status

  • Published

File Version

  • Published version

Journal

PLoS Computational Biology

ISSN

1553-734X

Publisher

Public Library of Science

Issue

10

Volume

12

Page range

1-41

Article number

e1005137

Department affiliated with

  • Informatics Publications

Research groups affiliated with

  • Centre for Computational Neuroscience and Robotics Publications
  • Evolutionary and Adaptive Systems Research Group Publications

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date

2016-10-21

First Open Access (FOA) Date

2016-10-21

First Compliant Deposit (FCD) Date

2016-10-21

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC