Increasing Selectivity to a Feature Combination Using Inhibitory Synaptic Plasticity in a Spiking Neural Network.

DOI
  • Ikeda Mahiro
    Graduate School of Information Science and Technology, Osaka Institute of Technology
  • Okuno Hirotsugu
    Faculty of Information Science and Technology, Osaka Institute of Technology

Description

In this study, we designed a spiking neural network that uses synaptic plasticity to increase selectivity to a particular combination of features. We investigated how the time constant of inhibitory presynaptic neurons whose weights were updated by the long-term potentiation of inhibition affects to selectivity of the postsynaptic neurons. The results showed that the selectivity was increased effectively when the time constant of inhibitory neurons was slightly longer than that of postsynaptic neurons.

Journal

Keywords

Details 詳細情報について

  • CRID
    1390859758187714560
  • DOI
    10.5954/icarob.2023.os22-1
  • ISSN
    21887829
  • Text Lang
    en
  • Data Source
    • JaLC
    • Crossref
    • OpenAIRE
  • Abstract License Flag
    Disallowed

Report a problem

Back to top