University of Sussex
Browse
Alearning_fullpaper_rev2.pdf (835.25 kB)

Input-modulation as an alternative to conventional learning strategies

Download (835.25 kB)
chapter
posted on 2023-06-09, 01:44 authored by Esin Yavuz, Thomas NowotnyThomas Nowotny
Animals use various strategies for learning stimulus-reward associations. Computational methods that mimic animal behaviour most commonly interpret learning as a high level phenomenon, in which the pairing of stimulus and reward leads to plastic changes in the final output layers where action selection takes place. Here, we present an alternative input-modulation strategy for forming simple stimulus-response associations based on reward. Our model is motivated by experimental evidence on modulation of early brain regions by reward signalling in the honeybee. The model can successfully discriminate dissimilar odours and generalise across similar odours, like bees do. In the most simplified connectionist description, the new input- modulation learning is shown to be asymptotically equivalent to the standard perceptron.

Funding

Odor-background segregation and source localization using fast olfactory processing; G1652; HUMAN FRONTIER SCIENCE PROGRAM (HFSP); RGP0053/2015

Green brain; G0924; EPSRC-ENGINEERING & PHYSICAL SCIENCES RESEARCH COUNCIL; EP/J019690/1

History

Publication status

  • Published

File Version

  • Accepted version

Publisher

Springer

Volume

9886

Page range

54-62

Pages

8.0

Book title

Proceedings of the ICANN 2016 Conference

ISBN

0302-9743

Series

Lecture Notes in Computer Science

Department affiliated with

  • Informatics Publications

Full text available

  • Yes

Peer reviewed?

  • Yes

Legacy Posted Date

2016-06-20

First Open Access (FOA) Date

2016-10-24

First Compliant Deposit (FCD) Date

2016-06-17

Usage metrics

    University of Sussex (Publications)

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC