Abstract
We present a model of a recurrent neural network with homeostasic units, embodied in a minimalist articulated agent with a single link and joint. The configuration of the agent is determined by the total activation level or kinetic energy of the network. We study the complexity patterns of the neural networks, and see how the entropy of the neural controller state and agent configuration changes with the relative characteristic time of the homeostasis when compared with the excitatory-inhibitory activation dynamics of network. We also present a meta-model of embodied neural agents, that serves as conceptual framework to study self-perturbation and the self-organization in embodied neural agents. Simulation results show that homeostasis significantly influences the dynamics of the network and the controlled agent, allowing the system to escape fixed-points and produce complex aperiodic behavior. The relation between the characteristic time of homeostasis and the characteristic time of main excitatory-inhibitory activation dynamics was found to be non-linear and non-monotonic. We use these findings to connect the perspectives of classical cybernetics on homeostasis to complexity research.
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.
Similar content being viewed by others
References
Maturana, H.R., Varela, F.J.: Autopoiesis and Cognition: the Realization of the Living. D. Reidel Publishing, Dordrecht (1980)
Reed, E.S.: Encountering the World: Toward an Ecological Psychology. Oxford University Press, New York (1996)
Pines, D., A., G., M., C.N.: Complexity: Metaphors, Models, and Reality. Perseus Books, Reading (1994)
Meyer, J.-A., Wilson, S.W.: From Animals to Animats: Proceedings of the First International Conference on Simulation of Adaptive Behavior. MIT Press, Cambridge (1991)
Varela, F.J., Bourgine, P.: Toward a Practice of Autonoumous Systems: Proceeding of the First European Conference on Artificial Life. MIT Press, Cambridge (1994)
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Natl. Acad. Sci. USA 70, 2554–2558 (1982)
Turrigiano, G., Nelson, S.B.: Homeostatic plasticity in the developing nervous system. Nature Reviews Neuroscience, 97–101 (2004)
Weng, J.: Developmental robots: theory and experiments. International Journal of Humanoid Robotics 1(2), 199–236 (2004)
Ashby, W.R.: Introduction to Cybernetics. Methuen, London (1956)
Beer, R.D.: Computational and dynamical languages for autonomous agents. In: Mind as motion: explorations in the dynamics of cognition table of contents, pp. 121–147. MIT Press, Cambridge (1996)
Strogatz, S.H.: Nonlinear Dynamics and Chaos: With Applications to Physics, Biology, Chemistry and Engineering. Perseus Books Group, Reading (1994)
Simão, J.P.: Self-perturbation and homeostasis in embodied recurrent neural networks: A meta-model and some explorations with mechanisms for sensorimotor coordination (submitted, 2007)
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. International Series on Advanced Intelligence, pp. 19–42. Advanced Knowledge International Press, Magill (2003)
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). Measuring Entropy in Embodied Neural Agents with Homeostasic Units: A Link Between Complexity and Cybernetics. In: Almeida e Costa, F., Rocha, L.M., Costa, E., Harvey, I., Coutinho, A. (eds) Advances in Artificial Life. ECAL 2007. Lecture Notes in Computer Science(), vol 4648. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-74913-4_95
Download citation
DOI: https://doi.org/10.1007/978-3-540-74913-4_95
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-74912-7
Online ISBN: 978-3-540-74913-4
eBook Packages: Computer ScienceComputer Science (R0)