Abstract
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.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kitano, H.: Toward a theory of biological robustness. Mol. Syst. Biol. 3, 137 (2007)
Fernandez-Leon, J.A., Di Paolo, E.A.: Neural uncertainty and sensorimotor robustness. In: Almeida e Costa, F., Rocha, L.M., Costa, E., Harvey, I., Coutinho, A. (eds.) ECAL 2007. LNCS (LNAI), vol. 4648, pp. 786–795. Springer, Heidelberg (2007)
Bays, P., Wolpert, D.: Computational principles of sensorimotor control that minimize uncertainty and variability. The Journal of Physiology 578(2), 387–396 (2007)
Jakobi, N.: Evolutionary robotics and the radical envelope of noise hypothesis. Journal of Adaptive Behaviour 6(2), 325–368 (1997)
Mathayomchan, B., Beer, R.: Center-crossing recurrent neural networks for the evolution of rhythmic behavior Source. Neural Comp. 14(9), 2043–2051 (2002)
Di Paolo, E.A., Harvey, I.: Decisions and noise: the scope of evolutionary synthesis and dynamical analysis. Adaptive Behavior 11(4), 284–288 (2004)
Beer, R.: On the dynamics of small continuous-time recurrent neural networks. Adaptive Behavior 3(4), 469–509 (1995)
Iizuka, H., Di Paolo, E.A.: Minimal agency detection of embodied agents. In: Almeida e Costa, F., Rocha, L.M., Costa, E., Harvey, I., Coutinho, A. (eds.) ECAL 2007. LNCS (LNAI), vol. 4648, pp. 485–494. Springer, Heidelberg (2007)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fernandez-Leon, J.A., Di Paolo, E.A. (2008). Neural Noise Induces the Evolution of Robust Behaviour by Avoiding Non-functional Bifurcations. In: Asada, M., Hallam, J.C.T., Meyer, JA., Tani, J. (eds) From Animals to Animats 10. SAB 2008. Lecture Notes in Computer Science(), vol 5040. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69134-1_4
Download citation
DOI: https://doi.org/10.1007/978-3-540-69134-1_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69133-4
Online ISBN: 978-3-540-69134-1
eBook Packages: Computer ScienceComputer Science (R0)