Stochastic Learning Algorithms for Modeling Human Category Learning

Most neural network (NN) models of human category learning use a gradient-based learning method, which assumes that locally-optimal changes are made to model parameters on each learning trial. This method tends to under predict variability in individual-level cognitive processes. In addition many recent models of human category learning have been criticized for not being able to replicate rapid changes in categorization accuracy and attention processes observed in empirical studies. In this paper we introduce stochastic learning algorithms for NN models of human category learning and show that use of the algorithms can result in (a) rapid changes in accuracy and attention allocation, and (b) different learning trajectories and more realistic variability at the individual-level.

Authors:

• Toshihiko Matsuka
• James E. Corter

Keywords:

• category learning
• cognitive modeling
• radial basis function
• stochastic optimization.

References:

[1] Kruschke, J. K. (1992). ALCOVE: An exemplar-based connectionist
model of category learning, Psychological Review, 99. 22-44.
[2] Kruschke, J. K., & Johansen, M. K. (1999). A model of probabilistic
category learning. Journal of Experimental Psychology: Learning,
Memory, and Cognition, 25, 1083-1119.
[3] Love, B. C. & Medin, D. L. (1998). SUSTAIN: A model of human
category learning. Proceeding of the Fifteenth National Conference on AI
(AAAI-98), 671-676.
[4] Matsuka, T. (2002). Attention processes in computational models of
category learning. Unpublished doctoral dissertation. Columbia
University, New York, NY.
[5] Matsuka, T. & Corter, J. E. (2003). Empirical studies on attention
processes in category learning. Poster presented at 44th Annual Meeting
of the Psychonomic Society. Vancouver, BC, Canada.
[6] Matsuka, T., Corter, J. E. & Markman, A. B. (2003). Allocation of
attention in neural network models of categorization. Under review
[7] Bower, G. H. & Trabasso, T. R. (1963). Reversals prior to solution in
concept identification. Journal of Experimental Psychology, 66, 409-418.
[8] Rehder, B. & Hoffman, A. B. (2003). Eyetracking and selective attention
in category learning [CD-ROM]. Proceedings of the 25th Annual Meeting
of the Cognitive Science Society, Boston, 2003.
[9] Macho, S. (1997). Effect of relevance shifts in category acquisition: A
test of neural networks. Journal of Experimental Psychology: Learning,
Memory, and Cognition, 23, 30-53.
[10] Ingber, L. (1998). Very fast simulated annealing. Journal of
Mathematical Modelling, 12: 967-973.
[11] Nosofsky, R. M. (1986). Attention, similarity and the identification
-categorization relationship. Journal of Experimental Psychology:
General, 115, 39-57
[12] Nosofsky, R. M., Palmeri, T. J., McKinley, S. C. (1994).
Rule-plus-exception model of classification learning. Psychological
Review, 101, 53-79
[13] Shepard, R. N., Hovland, C. L., & Jenkins, H. M. (1961). Learning and
memorization of classification. Psychological Monograph, 75 (13).
[14] Bettman, J. R., Johnson, E. J., Luce, M. F., Payne, J. W. (1993).
Correlation, conflict, and Choice. Journal of Experimental Psychology:
Learning, Memory, and Cognition, 19, 931-951.
[15] Nosofsky, R. M., Gluck, M. A., Palmeri, T. J., McKinley, S. C., &
Glauthier, P. (1994). Comparing models of rule-based classification
learning: A replication and extension of Shepard, Hovland, and Jenkins
(1961). Memory and Cognition, 22, 352-369.
[16] Matsuka, T. (In press). Generalized exploratory model of human category
learning. International Journal of Computational Intelligence.