World Scientific
  • Search
Skip main navigation

Cookies Notification

We use cookies on this site to enhance your user experience. By continuing to browse the site, you consent to the use of our cookies. Learn More
×
Our website is made possible by displaying certain online content using javascript.
In order to view the full content, please disable your ad blocker or whitelist our website www.worldscientific.com.

System Upgrade on Tue, Oct 25th, 2022 at 2am (EDT)

Existing users will be able to log into the site and access content. However, E-commerce and registration of new users may not be available for up to 12 hours.
For online purchase, please visit us again. Contact us at [email protected] for any enquiries.
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

    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

    References

    • J. Anderson, Psychol. Rev. 98, 409 (1991). Crossref, ISIGoogle Scholar
    • F. Ashby, S. Queller and P. M. Berretty, Percep. Psychophys. 61, 1178 (1999). Crossref, ISIGoogle 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, ISIGoogle Scholar
    • G. A. Carpenter and S. Grossberg, Comput. Vis. Graph. Imag. Proc. 37, 54 (1987). CrossrefGoogle Scholar
    • J. P. Clapper and G. H. Bower, Psychol. Learn. Motiv. 27, 65 (1991). Crossref, ISIGoogle Scholar
    • J. P. Clapper and G. H. Bower, J. Experim. Psychol. Learn. Mem. Cogn. 20, 443 (1994). Crossref, ISIGoogle Scholar
    • A.   Cleermans , Mechanisms of Implicit Learning: Connectionist Models of Sequence Processing ( MIT Press , Cambridge, MA , 1993 ) . CrossrefGoogle 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, ISIGoogle 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, ISIGoogle Scholar
    • H. S. Hock, L. Malcus and L. Hasher, J. Experim. Psychol. Learn. Mem. Cogn. 12, 232 (1986). Crossref, ISIGoogle Scholar
    • T.   Kohonen , Self-Organization and Associative Memory , 3rd edn. ( Springer , Berlin, Heidelberg , 1989 ) . CrossrefGoogle Scholar
    • J. Kruschke, Psychol. Rev. 99, 22 (1992). Crossref, ISIGoogle Scholar
    • P.   Lewicki , Nonconscious Social Information Processing ( Academic Press , NY , 1986 ) . Google Scholar
    • B. C. Love, Psychol. Bull. Rev. 9(4), 829 (2002). CrossrefGoogle 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, ISIGoogle Scholar
    • R. M. Nosofskyet al., Mem. Cogn. 22, 352 (1994). Crossref, ISIGoogle Scholar
    • R. M. Nosofsky, T. J. Palmeri and S. C. McKinley, Psychol. Rev. 101(1), 53 (1994). Crossref, ISIGoogle Scholar
    • R. Ratcliff, Psychol. Rev. 97, 285 (1990). Crossref, ISIGoogle Scholar
    • D. E. Rumelhart, G. E. Hinton and R. J. Williams, Nature 323, 533 (1986). Crossref, ISIGoogle Scholar
    • R. N. Shepard, Science 237, 1317 (1987). Crossref, ISIGoogle 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). CrossrefGoogle Scholar
    • B. Widrow and M. E. Hoff, Adaptive switching circuits, IRE WESCON Convention Record pp. 96–104. Google Scholar