Abstract
This study presents an extended model of homeostatic adaptation designed to exploit the internal dynamics of a neural network in the absence of sensory input. In order to avoid typical convergence to asymptotic states under these conditions plastic changes in the network are induced in evolved neurocontrollers leading to a renewal of dynamics that may favour sensorimotor adaptation. Other measures are taken to avoid loss of internal variability (as caused, for instance, by synaptic strength saturation). The method allows the generation of reliable adaptation to morphological disruptions in a simple simulated vehicle using a homeostatic neurocontroller that has been selected to behave homeostatically while performing the desired behaviour but non-homeostatically in other circumstances. The performance is compared with simple homeostatic neural controllers that have only been selected for a positive link between internal and behavioural stability. The extended homeostatic networks perform much better and are more adaptive to morphological disruptions that have never been experienced before by the agents.
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
Di Paolo, E.A.: Homeostatic adaptation to inversion in the visual field and other sensorimotor disruptions. In: From Animals to Animats VI: Proceedings of the 6th International Conference on Simulation of Adaptive Behavior, pp. 440–449 (2000)
Di Paolo, E.A.: Spike timing dependent plasticity for evolved robots. Adaptive Behavior 10(3/4), 243–263 (2002)
Hoinville, T., Henaff, P.: Evolving plastic neural controllers stabilized by homeostatic mechanisms for adaptation to a perturbation. In: Proceedings of the 9th International Conference on the Simulation and Synthesis of Living Systems, pp. 81–87 (2004)
Williams, H.: Homeostatic plasticity in recurrent neural networks. In: From Animals to Animats 8: Proceedings of the 8th International Conference on the Simulation of Adaptive Behavior, pp. 344–353 (2004)
Iizuka, H., Di Paolo, E.A.: Toward Spinozist robotics: Exploring the minimal dynamics of behavioural preference. Adaptive Behavior 15(4), 359–376 (2007)
Iizuka, H.: Evolving homeostatic neural controller without depending on initial weights. In: Proceedings of 13th International Symposium of Artificial Life and Robotics (2008)
Ashby, W.R.: Design for a brain: The origin of adaptive behaviour, 2nd edn. Chapman and Hall, London (1960)
Beer, R.D.: Intelligence as adaptive behavior: An experiment in computational neuroscience. Academic Press, San Diego (1990)
Beer, R.D.: Toward the evolution of dynamical neural networks for minimally cognitive behavior. In: From Animals to Animats 4: Proceedings of the 4th International Conference on Simulation of Adaptive Behavior, pp. 421–429 (1996)
Wood, R., Di Paolo, E.A.: New models for old questions: Evolutionary robotics and the ’A Not B’ error. In: Proceedings of 9th European Conference on Artificial Life, pp. 1141–1150 (2007)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Iizuka, H., Di Paolo, E.A. (2008). Extended Homeostatic Adaptation: Improving the Link between Internal and Behavioural Stability. 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_1
Download citation
DOI: https://doi.org/10.1007/978-3-540-69134-1_1
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)