Abstract
The traditional view of neural networks is algorithmic. The general learning problems are typically hard and powerful networks and learning algorithms such as MLPs with BP must be used. It is a well-known fact that the power of the learning algorithm required to solve a problem depends on the statistical distribution of the input data. If the distribution is known, a “taylored” network can be used. We argue that in the real-world the- distributions are not given, but can be generated in the process of sensory-motor coordination as the embodied autonomous agent interacts with its environment. It is shown that sensory-motor coordination can lead to dramatic reduction of learning comlexity in the information theoretic sense. The ideas discussed in this paper tie in with a set of design principles for autonomous agents that we have established over the last few years.
Preview
Unable to display preview. Download preview PDF.
References
Ashby, W.R.: An introduction to cybernetics. (1956) London: Chapman and Hall.
Pfeifer, R.: Building “Fungus Eaters”: Design principles of autonomous agents. In: P. Maes, M. Mataric, J-A. Meyer, J. Pollack, and S.W. Wilson (eds.), From animals to animals 4. Proc. of the 4th Int. Conference on Simulation of Adaptive Behavior Cambridge, Mass.: MIT Press (1996) 3–13.
Pfeifer, R. and Scheier, C..: Sensory-motor coordination: the metaphor and beyond. In R. Pfeifer, and R. Brooks (eds.). Robotics and Autonomous Systems, Special Issue on “Practice and Future of Autonomous Agents.” 20 (1997) Nos. 2–4.
Scheier, C. and Pfeifer, R.: Classification as sensory-motor coordination. In: F. Moran, A. Moreno, J.J. Merelo and P. Chacon (eds.) Advances in Artificial Life. Proceedings of the Third European Conference on Artificial Life ECAL95 (1995) 656–667
Shannon, C.E., and Weaver, W.: The mathematical theory of communication. Urbana, Ill. University of Illinois Press (1949)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Scheier, C., Pfeifer, R. (1997). Information theoretic implications of embodiment for neural network learning. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020234
Download citation
DOI: https://doi.org/10.1007/BFb0020234
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive