Nonlinear mapping with minimal supervised learning
- 4 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1, 170-179 vol.1
- https://doi.org/10.1109/hicss.1990.205113
Abstract
The problem of interpolating unknown mappings from known mappings is addressed. This problem arises when a large number of mappings must be learned and it is impractical to train the network on all possible mappings. Described is a network model that can learn nonlinear mappings with a minimal amount of supervised training. A combination of supervised and supervised learning is used to train the network. It is shown that the network is able to interpolate mappings on which it has not been previously trained.Keywords
This publication has 10 references indexed in Scilit:
- A self-organizing neural network for classifying sequencesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- The 'neural' phonetic typewriterComputer, 1988
- Comparing generalization by humans and adaptive networksNeural Networks, 1988
- Generalization in digital functionsNeural Networks, 1988
- The emergence of generalization in networks with constrained representationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- An adaptive 'broom balancer' with visual inputsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- Neural net pruning-why and howPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- Topology conserving mappings for learning motor tasksAIP Conference Proceedings, 1986
- Analysis of a simple self-organizing processBiological Cybernetics, 1982
- Self-organized formation of topologically correct feature mapsBiological Cybernetics, 1982