Abstract
In this paper we analyze how supervised learning occurs in ecological neural networks, i.e. networks that interact with an autonomous external environment and, therefore, at least partially determine with their behavior their own input. Using an evolutionary method for selecting good teaching inputs we surprisingly find that to obtain a desired outputX it is better to use a teaching input different fromX. To explain this fact we claim that teaching inputs in ecological networks have two different effects: (a) to reduce the discrepancy between the actual output of the network and the teaching input, (b) to modify the network's behavior and, as a consequence, the network's learning experiences. Evolved teaching inputs appear to represent a compromise between these two needs. We finally show that evolved teaching inputs that are allowed to change during the learning process function differently at different stages of learning, first giving more weight to (b) and, later on, to (a).
Similar content being viewed by others
References
D. Parisi, F. Cecconi, S. Nolfi. Econets: Neural Networks that Learn in an Environment.Network, 1, pp. 149–168, 1990
D.E. Rumelhart, G.E. Hinton, R. J. Williams. Learning internal representations by error propagation. In D.E. Rumelhart, and J.L. McClelland (eds.),Parallel Distributed Processing Vol.1, Foundations, Cambridge, Mass., MIT Press, 1986.
J.J. Holland.Adaptation in Natural and Artificial Systems. Ann Arbor, Michigan, University of Michigan Press, 1975.
J.L. Elman. Incremental learning, or the importance of starting small. Center for Research in Language,Technical Report 9101, University of California San Diego, 1991.
K. Plunkett, and V. Marchman. U-shaped learning and frequency effects in a multi-layered perceptron: implications for child language acquisition.Cognition, 38, pp. 43–102, 1991.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Nolfi, S., Parisi, D. Good teaching inputs do not correspond to desired responses in ecological neural networks. Neural Process Lett 1, 1–4 (1994). https://doi.org/10.1007/BF02310934
Issue Date:
DOI: https://doi.org/10.1007/BF02310934