SPECIAL ISSUE: Tools and Techniques of Artificial Intelligence; Edited by I. Russell and S. HallerNo Access

Human Unsupervised and Supervised Learning as a Quantitative Distinction

Todd M. Gureckis

Department of Psychology, University of Texas at Austin, 1 University Station A8000, Austin, TX 78712-0187, USA

Search for more papers by this author

and

Bradley C. Love

Department of Psychology, University of Texas at Austin, 1 University Station A8000, Austin, TX 78712-0187, USA

Search for more papers by this author

https://doi.org/10.1142/S0218001403002587Cited by:5 (Source: Crossref)

Abstract

SUSTAIN (Supervised and Unsupervised STratified Adaptive Incremental Network) is a network model of human category learning. SUSTAIN initially assumes a simple category structure. If simple solutions prove inadequate and SUSTAIN is confronted with a surprising event (e.g. it is told that a bat is a mammal instead of a bird), SUSTAIN recruits an additional cluster to represent the surprising event. Newly recruited clusters are available to explain future events and can themselves evolve into prototypes/attractors/rules. SUSTAIN has expanded the scope of findings that models of human category learning can address. This paper extends SUSTAIN to account for both supervised and unsupervised learning data through a common mechanism. The modified model, uSUSTAIN (unified SUSTAIN), is successfully applied to human learning data that compares unsupervised and supervised learning performances.¹⁸

Keywords:

References

J. Anderson, Psychol. Rev. 98, 409 (1991). Crossref, Web of Science, Google Scholar
F. Ashby, S. Queller and P. M. Berretty, Percep. Psychophys. 61, 1178 (1999). Crossref, Web of Science, Google Scholar
D. C. Berry and Z. Dienes , Implicit Learning: Theoretical and Empirical Issues ( Erlbaum , Hillsdale, NJ , 1993 ) . Google Scholar
D. Billman and J. Knutson, J. Experim. Psychol. Learn. Mem. Cogn. 22(2), 458 (1996). Crossref, Web of Science, Google Scholar
G. A. Carpenter and S. Grossberg, Comput. Vis. Graph. Imag. Proc. 37, 54 (1987). Crossref, Google Scholar
J. P. Clapper and G. H. Bower, Psychol. Learn. Motiv. 27, 65 (1991). Crossref, Web of Science, Google Scholar
J. P. Clapper and G. H. Bower, J. Experim. Psychol. Learn. Mem. Cogn. 20, 443 (1994). Crossref, Web of Science, Google Scholar
A. Cleermans , Mechanisms of Implicit Learning: Connectionist Models of Sequence Processing ( MIT Press , Cambridge, MA , 1993 ) . Crossref, Google Scholar
T. Gureckis and B. C. Love, Modeling unsupervised learning with sustain, Proc. 15th Annual FLAIRS Conf. pp. 163–167. Google Scholar
T. Gureckis and B. C. Love, J. Experim. Th. Artif. Intell. 15, 1 (2003). Crossref, Web of Science, Google Scholar
T. Gureckis and B. C. Love, Who says models can only do what you tell them? unsupervised category learning data, fits, and predictions, Proc. 24th Ann. Conf. Cognitive Science Society (Lawrence Erlbaum Associates, 2002) pp. 399–404. Google Scholar
J. A. Hartigan , Clustering Algorithms ( Wiley , NY , 1975 ) . Google Scholar
N. Hayes and D. E. Broadbent, Cognition 28, 249 (1988). Crossref, Web of Science, Google Scholar
H. S. Hock, L. Malcus and L. Hasher, J. Experim. Psychol. Learn. Mem. Cogn. 12, 232 (1986). Crossref, Web of Science, Google Scholar
T. Kohonen , Self-Organization and Associative Memory , 3rd edn. ( Springer , Berlin, Heidelberg , 1989 ) . Crossref, Google Scholar
J. Kruschke, Psychol. Rev. 99, 22 (1992). Crossref, Web of Science, Google Scholar
P. Lewicki , Nonconscious Social Information Processing ( Academic Press , NY , 1986 ) . Google Scholar
B. C. Love, Psychol. Bull. Rev. 9(4), 829 (2002). Crossref, Google Scholar
B. C. Love, A. B. Markman and T. Yamauchi, Modeling classification and inference learning, Proc. Fifteenth Nat. Conf. Artificial Intelligence pp. 136–141. Google Scholar
B. C. Love and D. L. Medin, Modeling item and category learning, Proc. 20th Ann. Conf. Cognitive Science Society (Lawrence Erlbaum Associates, 1998) pp. 639–644. Google Scholar
B. C. Love and D. L. Medin, SUSTAIN: a model of human category learning, Proc. Fifteenth Nat. Conf. Artificial Intelligence (MIT Press, 1998) pp. 671–676. Google Scholar
B. C. Love, D. L. Medin and T. Gureckis, "SUSTAIN: a network model of human category learning," Psychol. Rev. (2002) in press . Google Scholar
R. D. Luce , Individual Choice Behavior: A Theoretical Analysis ( Greenwood Press , Westport, CN , 1959 ) . Google Scholar
D. L. Medin and P. J. Schwanenflugel, J. Experim. Psychol.: Human Learn. Mem. 7, 355 (1981). Crossref, Web of Science, Google Scholar
R. M. Nosofskyet al., Mem. Cogn. 22, 352 (1994). Crossref, Web of Science, Google Scholar
R. M. Nosofsky, T. J. Palmeri and S. C. McKinley, Psychol. Rev. 101(1), 53 (1994). Crossref, Web of Science, Google Scholar
R. Ratcliff, Psychol. Rev. 97, 285 (1990). Crossref, Web of Science, Google Scholar
D. E. Rumelhart, G. E. Hinton and R. J. Williams, Nature 323, 533 (1986). Crossref, Web of Science, Google Scholar
R. N. Shepard, Science 237, 1317 (1987). Crossref, Web of Science, Google Scholar
R. N. Shepard, C. L. Hovland and H. M. Jenkins, Psychol. Monogr. 75, 13 (1961). Google Scholar
S. A. Sloman, Thinking & Reasoning 3, 81 (1997). Crossref, Google Scholar
B. Widrow and M. E. Hoff, Adaptive switching circuits, IRE WESCON Convention Record pp. 96–104. Google Scholar