Abstract
One of the key ideas in both robotics and neuroscience (and emphasized in this volume) is that complex behaviour can arise from the interaction of many cooperating simple agents or modules. However, while intelligent behaviour is thought to be obtained from combining modules, it has been common practice to study the development of individual modules or systems in isolation. In this paper we argue that combining modules during learning can help solve the teaching signal dilemma and allow the system to learn without an external teaching signal.
This research was supported by a grant from the Human Frontier Science Program and by a Canadian NSERC 1967 Science and Engineering Scholarship
This is a preview of subscription content, log in via an institution to check access.
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
Becker, S. (1996). Mutual information maximization: Models of cortical self-organization. Network: Computation in Neural Systems 7 7–31.
Becker, S., & G.E. Hinton (1992). A self-organizing neural network that discovers surfaces in random-dot stereograms. Nature 355 161–163.
Buser, P., & P. Borenstein (1959). Responses somesthesiques, visuel et auditives, recueilles, au niveau du cortex “associatif” infrasylvien chez le chat curarise non anesthesie. Revue d’Electroencéphalographie et de Neurophysiologie Clinique 11 285–304.
de Sa, V.R. (1994a). Learning classification with unlabeled data. In J. Cowan, G. Tesauro, & J. Alspector (eds.), Advances in neural information processing systems6 (pp. 112–119). San Francisco, CA: Morgan Kaufman.
de Sa, V.R. (1994b). Minimizing disagreement for self-supervised classification. In M. Mozer, P. Smolensky, D. Touretzky, J. Elman, & A. Weigend (eds.), Proceedings of the 1993 Connectionist Models Summer School (pp. 300–307). Hillsdale, NJ: Lawrence Erlbaum Assoc.
de Sa, V.R. (1994c). Unsupervised classification learning from cross-modal environmental structure. PhD thesis, Department of Computer Science, University of Rochester, Rochester, NY. Also available as TR 536 (November 1994).
de Sa, V.R., & D.H. Ballard (1993). Self-teaching through correlated input. In F.H. Eeckman & J.M. Bower (eds.), Computation and neural systems1992 (pp. 437–441). Dordrecht, The Netherlands: Kluwer.
de Sa, V.R., & D.H. Ballard (1998). Category learning through multimodality sensing. Neural Computation 10(5), 1097–1117.
Diamantini, C., & A. Spalvieri (1995). Pattern classification by the bayes machine. Journal of Experimental Psychology 34(2), 87–103.
Durgin, F.H. (1995). Contingent aftereffects of texture density: Perceptual learning and contingency. PhD thesis, Department of Psychology, University of Virginia.
Durgin, F.H., & D.R. Proffitt (1996). Visual learning in the perception of texture: Simple and contingent aftereffects of texture density. Spatial Vision 9(4), 423–474.
Fishman, M.C., & C.R. Michael (1973). Integration of auditory information in the cat’s visual cortex. Vision Research 13 1415–1419.
Grossberg, S. (1976). Adpative pattern classification and universal recoding: I. Parallel development and coding of neural feature detectors. Biological Cybernetics 23 121–134.
Haenny, P., J. Maunsell, & P. Schiller (1988). State dependent activity in monkey visual cortex. II. Retinal and extraretinal factors in V4. Experimental Brain Research 69(2), 245–259.
Howells, T. (1944). The experimental development of color-ton synthesia. Journal of Experimental Psychology 34(2), 87–103.
Kay, J., D. Floreano, & W. Phillips (1998). Contextually guided unsupervised learning using local multivariate binary processors. Neural Networks 11(1), 117–140.
Kohonen, T. (1982). Self-organized formation of topologically correct feature maps. Biological Cybernetics 43 59–69.
Kohonen, T. (1990). Improved versions of learning vector quantization. IJCNN International Joint Conference on Neural Networks, volume 1 (pp. I/545–I/550). New York: IEEE Neural Network Council.
Kühl, P.K., & A.N. Meltzoff (1984). The intermodal representation of speech in infants. Infant Behavior and Development 7 361–381.
Lapedes, A., E. Steeg, & R. Farber (1994). Neural network definitions of highly predictable protein secondary structure classes. In J. Cowan, G. Tesauro, & J. Alspector (eds.), Advances in neural information processing systems6 (pp. 809–816). San Francisco, CA: Morgan Kaufman.
MacDonald, J., & H. McGurk (1978). Visual influences on speech perception processes. Perception & Psychophysics 24(3), 253–257.
Maunsell, J., G. Sclar, T. Nealey, & D. DePriest (1991). Extraretinal representations in area V4 of macaque monkey. Visual Neuroscience 7(6), 561–573.
McGurk, H., & J. MacDonald (1976). Hearing lips and seeing voices. Nature 264 746–748.
Meulders, M., J. Colle, & N. Biosacq-Schepens (1965). Macro and microelectrode studies of somatic responses in the lateral geniculate body. Proceedings, XXIII International Congress of Physiological Sciences (p. 364). Tokyo.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
De Sa, V.R. (2000). Combining Uni-Modal Classifiers to Improve Learning. In: Cruse, H., Dean, J., Ritter, H. (eds) Prerational Intelligence: Adaptive Behavior and Intelligent Systems Without Symbols and Logic, Volume 1, Volume 2 Prerational Intelligence: Interdisciplinary Perspectives on the Behavior of Natural and Artificial Systems, Volume 3. Studies in Cognitive Systems, vol 26. Springer, Dordrecht. https://doi.org/10.1007/978-94-010-0870-9_74
Download citation
DOI: https://doi.org/10.1007/978-94-010-0870-9_74
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-010-3792-1
Online ISBN: 978-94-010-0870-9
eBook Packages: Springer Book Archive