University of Sussex
Browse

File(s) not publicly available

Neural noise induces the evolution of robust behaviour by avoiding non-functional bifurcations

presentation
posted on 2023-06-08, 10:18 authored by Jose Fernandez Leon, Ezequiel Di Paolo
Continuous-time recurrent neural networks affected by random additive noise are evolved to produce phototactic behaviour in simulated mobile agents. The resulting neurocontrollers are evaluated after evolution against perturbations and for different levels of neural noise. Controllers evolved with neural noise are more robust and may still function in the absence of noise. Evidence from behavioural tests indicates that robust controllers do not undergo noise-induced bifurcations or if they do, the transient dynamics remain functional. A general hypothesis is proposed according to which evolution implicitly selects neural systems that operate in noise-resistant landscapes which are hard to bifurcate and/or bifurcate while retaining functionality.

History

Publication status

  • Published

Publisher

From Animals to Animats 10, Springer

Presentation Type

  • paper

Event name

10th International Conference on the Simulation of Adaptive Behavior

Event location

Japan

Event type

conference

Department affiliated with

  • Informatics Publications

Full text available

  • No

Peer reviewed?

  • Yes

Legacy Posted Date

2012-02-20

Usage metrics

    University of Sussex (Publications)

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC