Research > Research Centers > Decision Technologies > Research Areas/Publications > Human/Machine Learning

Sitemap Print People Finder

Human and Machine Learning

The ability to use prior experiences to guide behaviors in novel situations is critical to all intelligent agents operating in complex environments. In this area of research, we study how humans learn from past experiences by conducting human behavioral experiments and developing computational models that explain the observed behaviors, with primary emphases on category learning, attention, memory, and knowledge representation. Based on the results from human experiments and computer simulations, we develop adaptive systems or machines that display effective learning in varying environments and devise decision and training aids that improve people's performance.

A primary goal of this line of work is to apply our understanding of human cognition to help solve real world problems, such as detecting hostile intent, distributing sensors, understanding social networks, and improving education.

Publications

Sakamoto, Y., Matsuka, T., & Love, B. C. (in preparation). Modeling Enhanced Oddball Memory by Flexible and Rapid Attention Shifting.

Sakamoto, Y., & Love, B. C. (in preparation). Facilitating Learning of Correlations through Inference in a Classroom Setting.

Sakamoto, Y., Love, B. C., & Jones, M. (in preparation). Contrasting Statistical and Similarity-Driven Learning: Variability's Influence on Categorization.

Matsuka, T., Sakamoto, Y., & Nickerson, J. V. (under review). OEDIPUS: A Prototype Model That Learns and Generalize Category Knowledge Like Humans Do. Under review.

Matsuka, T. & Sakamoto, Y. (2007). A Model of Cocept Learning with a Flexible Representation System. Lecture Notes in Computer Science (LNCS Vol. xxxx), Advances in Neural Networks, (pp. xxx-xxx). Berlin: Springer-Verlag. Forthcoming

Matsuka, T., Sakamoto, Y., Nickerson, J. V., & Chouchourelou, A. (2006). A Cognitive Model of Multi-Objective Multi-Concept Formation. Lecture Notes in Computer Science (LNCS Vol. 4131), Artificial Neural Networks, (pp. 563-572). Berlin: Springer-Verlag.

Sakamoto, Y., & Love, B. C. (2006). Vancouver, Toronto, Montreal, Austin: Enhanced oddball memory through differentiation, not isolation. Psychonomic Bulletin & Review, 13, 474-479.

Matsuka, T., Nickerson, J. V., & Jian, J-Y. (2006). A prototype model that learns and generalizes Medin, Alton, Edelson, & Frecko (1982) XOR category structure like humans do. In R. Sun and N. Miyake (Eds.), Proceedings of the 28^th Annual Conference of the Cognitive Science Society. Vancouver, Canada: Cognitive Science Society.

Sakamoto, Y., & Love, B. C. (2006). Sizable Sharks Swim Swiftly: Learning Correlations through Inference in a Classroom Setting. In R. Sun and N. Miyake (Eds.), Proceedings of the 28^th Annual Conference of the Cognitive Science Society. Vancouver, Canada: Cognitive Science Society.

Sakamoto, Y., Love, B. C., & Jones, M. (2006). Tracking Variability in Learning: Contrasting Statistical and Similarity-Based Accounts. In R. Sun and N. Miyake (Eds.), Proceedings of the 28^th Annual Conference of the Cognitive Science Society. Vancouver, Canada: Cognitive Science Society.

Sakamoto, Y. (2006). Acquiring New Speech Sounds by Clustering. In R. Sun and N. Miyake (Eds.), Proceedings of the 5^th International Conference of the Cognitive Science Society. Vancouver, Canada: Cognitive Science Society.

Matsuka, T., & Chouchourelou, A. (2006). A model of human category learning with dynamic multi-objective hypotheses testing with retrospective verification. Proceedings of the IEEE World Congress on Computational Intelligence International Joint Conference on Neural Networks.

Matsuka, T., & Nickerson, J. V. (2006). Modeling human hypothesis testing behaviors with simulated evolutionary processes, Proceedings of the IEEE World Congress on Computational Intelligence International Conference on Evolutionary Computation.

Matsuka, T. (2006). A Model of Category Learning with Attention Augmented Simplistic Prototype Representation. In J. Wang, Z. Yi, J. M. Zurada, B-L. Lu,& H. Yin (Eds.), Lecture Notes in Computer Science (LNCS Vol. 3971), Advances in Neural Networks, (pp. 34-40). Berlin: Springer-Verlag.

Matsuka, T., & Chouchourelou, A. (2006). On the learning algorithms of descriptive models of high-order human cognition. Lecture Notes in Computer Science (LNCS Vol.3971), Advances in Neural Networks, ISNN, (pp. 41-49). Berlin: Springer-Verlag.

Matsuka, T. (2005). Modeling human learning as context dependent knowledge utility optimization. In L. Wang, K. Chen, and Y. S. Ong (Eds.), Lecture Notes in Computer Science (LNCS Vol. 3601), Advances in Natural Computation, ICNC, (pp. 933-946). Berlin: Springer-Verlag.

Matsuka, T. , Yamauchi, T., Hanson, C., & Hanson, S. J. (2005). Representing categorical knowledge: An fMRI Study. In B. G. Bara, L. W. Barsalou, and M. Bucciarelli (Eds.), Proceedings of the 27^th Annual Conference of the Cognitive Science Society. Stresa, Italy: Cognitive Science Society.

Matsuka, T. (2005). Attention augmented prototype representation. In B. G. Bara, L. W. Barsalou, and M. Bucciarelli (Eds.), Proceedings of the 27^th Annual Conference of the Cognitive Science Society. Stresa, Italy: Cognitive Science Society.

Sakamoto, Y., & Love, B. C. (2005). A novel approach to understanding novelty effects in memory. In B. G. Bara, L. W. Barsalou, and M. Bucciarelli (Eds.), Proceedings of the 27^th Annual Conference of the Cognitive Science Society. Stresa, Italy: Cognitive Science Society.

Matsuka, T. (2005). Simple, individually unique, and context-dependent learning methods for models of human category learning. Behavior Research Methods, 37, 240–255.

Sakamoto, Y., & Love, B. C. (2004). Schematic influences on category learning and recognition memory. Journal of Experimental Psychology: General, 133, 534-553.

Matsuka, T., & Corter, J.E. (2004). Stochastic learning algorithm for modeling human category learning. International Journal of Computational Intelligence, 1, 40-48.

Matsuka, T. (2004). Biased stochastic learning in computational model of category learning. In K. Forbus, D. Gentner, and T. Regier (Eds.), Proceedings of the 26^th Annual Conference of the Cognitive Science Society (pp. 915-920). Chicago, Il: Cognitive Science Society.

Matsuka, T. (2004). Comparisons of prototype- and exemplar-based neural network models of categorization using the GECLE framework. In K. Forbus, D. Gentner, and T. Regier (Eds.), Proceedings of the 26^th Annual Conference of the Cognitive Science Society (pp. 909-914). Chicago, Il: Cognitive Science Society.

Sakamoto, Y., & Love, B. C. (2004). Type/token information in category learning and recognition. In K. Forbus, D. Gentner, and T. Regier (Eds.), Proceedings of the 26^th Annual Conference of the Cognitive Science Society (p. 1626). Chicago, Il: Cognitive Science Society.

Matsuka, T. (2004). Generalized exploratory model of human category learning. International Journal of Computational Intelligence, 1, 7-15.

Matsuka, T., Corter, J. E., & Hanson, S. J. (2004) Irresistibly attractive fruitless feature dimensions. In M. Lovett, C. Schunn, C. Lebiere, and P. Munro (Eds.), Proceedings of the 6^th International Meeting of Cognitive Modeling (pp. 370-371). Mahwah, NJ: Lawrence Erlbaum Associates.

Matsuka, T., & Corter, J. E. (2004). Modeling human category learning with stochastic optimization methods. In M. Lovett, C. Schunn, C. Lebiere, and P. Munro (Eds.), Proceedings of the 6^th International Meeting of Cognitive Modeling (pp. 196-201). Mahwah, N: Lawrence Erlbaum Associates.

Matsuka, T. (2004). Exploratory approach for modeling human category learning. In M. Lovett, C. Schunn, C. Lebiere, and P. Munro (Eds.), Proceedings of the 6^th International Meeting of Cognitive Modeling (pp. 190-195). Mahwah, NJ: Lawrence Erlbaum Associates.

Sakamoto, Y., Matsuka, T., & Love, B. C. (2004). Dimension-wide vs. exemplar-specific attention in category learning and recognition. In M. Lovett, C. Schunn, C. Lebiere, and P. Munro (Eds.), Proceedings of the 6^th International Conference on Cognitive Modeling (pp. 261-266). Mahwah, NJ: Lawrence Erlbaum.

Matsuka, T., & Corter, J. E. (2003). Stochastic learning in neural network models of categorization. In R. Alterman and D. Kirsh (Eds.), Proceedings of the 25^th Annual Meeting of the Cognitive Science Society. Boston, MA: Cognitive Science Society.

Sakamoto, Y., & Love, B. C. (2003). Category structure and recognition memory. In R. Alterman and D. Kirsh (Eds.), Proceedings of the 25^th Annual Conference of the Cognitive Science Society (pp. 1017-1022). Boston, MA: Cognitive Science Society.

Goldstone, R. L., & Sakamoto, Y. (2003). The transfer of abstract principles governing complex adaptive systems. Cognitive Psychology, 46, 414-466.

Matsuka, T., Corter, J. E., & Markman, A. B. (2002). Allocation of attention in neural network models of categorization. Proceedings of the 24^th Annual Meeting of the Cognitive Science Society.

Presentations

TBA