Abstract
An investigation is performed to assess the generalization capability found in neural network paradigms to approximate a 2-dimensional coordinate (topological) transformation. A developed strategy uses the example to give a physical meaning to what is meant by generalization. The example shows how to use a neural network paradigm to generalize a two-degree of freedom topological transformation from cartesian end-point coordinates to corresponding joint angle coordinates based only on examples of the mapping. The importance of this example is that it provides a clear understanding of how and what a neural network is actually communications and brings a theoretical idea to a useful understanding. When examples characterize the topology, a collective generalization property begins to emerge and the network learns the topology. If the network is presented with additional examples of the transformation, the network can generate the corresponding joint angles to any unseen position, that is, by generalization. It is also significant that the network's generalization property emerges from the network based on very few training examples! Further, the networks power exists with very few neurons. Results suggest the use of the paradigm's generalization capability to provide solutions to unknown or intractable algorithms for applications.
Similar content being viewed by others
References
Caianiello ER (1961) Outline of thinking-machines and thought-processes. J Theor Biol 1:204–235
Hopfield JJ (1982) Neural networks and physical systems with emergent collective computational abilities. Proc Natl Acad Sci USA 79:2554–2558
Hopfield JJ, Tank DW (1985) Neural computation of decisions in optimization problems. Biol Cybern 52:147–152
Josin GM (1977) Self-control in neural networks. Biol Cybern 27:185–187
Josin GM (1986) In: Cotterill E (ed) Neural systems for uses as a research tool, computer simulation in brain science. Cambridge University Press, Cambridge
Josin GM (1987) Feasibility of using neural networks for robotic trajectory control strategy. JPL Report 958002
Rumelhart DE, McClelland JL, the PDP Research Group (1986) Parallel distributed processing. MIT/Bradford Book, Cambridge
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Josin, G. Neural-space generalization of a topological transformation. Biol. Cybern. 59, 283–290 (1988). https://doi.org/10.1007/BF00332917
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF00332917