Abstract
We present a model of a recurrent neural network, embodied in a minimalist articulated agent with a single link and joint. The configuration of the agent defined by one angle (degree of freedom), is determined by the activation state of the neural network. This is done by contracting a muscle with many muscular fibers, whose contraction state needs to be coordinated to generate high amplitude link displacements. In networks without homeostasic (self-regulatory) mechanism the neural state dynamics and the configuration state dynamics converges to a fixed point. Introduction of random noise, shows that fixed points are meta-stable. When neural units are endowed with homeostasic mechanisms in the form of threshold adjustment, the dynamics of the configuration angle and neural state becomes aperiodic. Learning mechanisms foster functional and structural cluster formation, and modifies the distribution of the kinetic energy of the network. We also present a meta-model of embodied neural agents, that identifies self-perturbation as a mechanism for neural development without a teacher.
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
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. USA 70, 2554–2558 (1982)
Weng, J.: Developmental robots: theory and experiments. International Journal of Humanoid Robotics 1(2), 199–236 (2004)
McClelland, J.L., Rumelhart, D.E.: Parallel Distributed Processing: Explorations in the Microstructure of Cognition. MIT Press, Cambridge (1986)
Turrigiano, G., Nelson, S.B.: Homeostatic plasticity in the developing nervous system. Nature Reviews Neuroscience, 97–101 (2004)
Vogels, T.P., Rajan, K., Abbott, L.F.: Neural network dynamics. Annual Review of Neuroscience 28(1), 357–376 (2005)
Cessac, B., Samuelides, M.: From neuron to neural network dynamics. In Topics in Dynamical Neural Networks : From Large Scale Neural Networks to Motor Control and Vision (EPJ special issue). Forthcoming.
Di Paolo, E.A.: Organismically-inspired robotics: Homeostatic adaptation and natural teleology beyond the closed sensorimotor loop. In: Dynamical Systems Approach to Embodiment and Sociality, Advanced Knowledge International, International Series on Advanced Intelligence, pp. 19–42. Advanced Knowledge International Press, Magill, Australia (2003)
Harter, D., Kozma, R.: Aperiodic dynamics and the self-organization of cognitive maps in autonomous agents. International Jounral on Artificial Intelligence Tools 21(9), 955–971 (2005)
Freeman, W.J.: How Brains Make Up Their Minds. Columbia University Press (2001)
Victor M. Eguìluz, Dante R. Chialvo, Guillermo A. Cecchi, Marwan Baliki, and A. Vania Apkarian. Scale-free brain functional networks. Physical Review Letters, 94(1), 018102.1–4 (2005)
Nolfi, S.: Behaviour as a complex adaptive system: On the role of self-organization in the development of individual and collective behaviour. ComplexUs, 2(3–4), 195–203 (2004/2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Simão, J. (2007). Self-perturbation and Homeostasis in Embodied Recurrent Neural Networks: A Meta-model and Some Explorations with Mechanisms for Sensorimotor Coordination. In: de Sá, J.M., Alexandre, L.A., Duch, W., Mandic, D. (eds) Artificial Neural Networks – ICANN 2007. ICANN 2007. Lecture Notes in Computer Science, vol 4669. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74695-9_95
Download citation
DOI: https://doi.org/10.1007/978-3-540-74695-9_95
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74693-5
Online ISBN: 978-3-540-74695-9
eBook Packages: Computer ScienceComputer Science (R0)