Abstract
Learning by changing connection weights only is time-consuming and does not always work. Freedom to modify network structure is also needed. Grow-and-Learn (GAL) is a new algorithm that is able to quantize vectors as members of categories in an incremental fashion. When a new vector is encountered, it is tested as in nearest neighbor search and if it is not already quantized correctly, unit and links are added to accommodate this additional requirement. Thus network when learning, grows if and when necessary. As the structure of the resulting network in such a learning phase is dependent on the order of encountering the vectors, a second phase is added to eliminate old, no-longer necessary associations. In this phase, the network is closed to the environment and the input patterns are generated by the network itself during which relevance of units are computed and those who are not vital are removed. Simulation results when applied to character recognition is promising. Physiological plausibility and how the idea may be extended to unsupervised learning is discussed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Barlow, H.B. (1989). “Unsupervised learning,” Neural Computation, 1, 295–311.
Blayo, F., Lehmann, C. (in review). “A systolic implementation of the self-organization algorithm,” submitted for review to INNC 90,Paris-France.
Baum, E.B. (1989). “A proposal for more powerful learning algorithms,” Neural Computation, 1, 201–207.
Crick, F., Mitchison, G. (1983). “The function of dream sleep,” Nature, 304–14, 111–114.
Dawkins, R. (1971). “Selective neurone death as a possible memory mechanism,” Nature, 229, 118–119.
Guyon, I., Poujaud, I., Personnaz, L., Dreyfus, G., Denker, J., and Le Cun, Y. (1989). “Comparing different neural network architectures for classifying handwritten digits,” Proc. IJCNN 89, Washington-USA.
Hubel, D.H. (1988). Eye, Brain, and Vision, New York: Scientific American Library.
Kandel, E.R., Schwartz, J.H. (1985). Principles of Neural Science, 2nd edition, New York: Elsevier.
Mozer, M.C., Smolensky, P. (1989). “Skeletonization: A technique for trimming the fat from a network via relevance assessment,” Connection Science, 1, 3–26.
Reilly, D.L., Cooper, L.N., and Elbaum, C. (1982). “A neural model for category learning,” Biological Cyhernetics, 45, 35–41.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 1990 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Alpaydm, E. (1990). Grow-and-Learn: An Incremental Method for Category Learning. In: International Neural Network Conference. Springer, Dordrecht. https://doi.org/10.1007/978-94-009-0643-3_69
Download citation
DOI: https://doi.org/10.1007/978-94-009-0643-3_69
Publisher Name: Springer, Dordrecht
Print ISBN: 978-0-7923-0831-7
Online ISBN: 978-94-009-0643-3
eBook Packages: Springer Book Archive