Investigations of an Exemplar-Based Connectionist Model of Category Learning

Publisher Summary This chapter discusses that learning to categorize objects stands among the most fundamental cognitive processes. Categorizing brings order and organization to our mental lives and is a building block of more complex cognitive processes such as reasoning, problem solving, and thinking. Central issues in the study of categorization include how categories are represented in memory, and what decision processes are involved when people make categorization judgments. It provides an overview of ALEX and discusses its relation to the context model. It explains applications of the model in a variety of category learning situations. The context model and ALEX are also compared. It applies ALEX to several previously published data sets that have been fitted accurately by the context model. The main goal is to provide some quantitative tests of ALEX and demonstrate that it performs well in situations in which the context model has performed well. It also discusses the advantages that are yielded by elaborating the context model as an exemplar-based network. The chapter demonstrates a variety of phenomena that are characterized well by ALEX but not by the context model. There is also some discussion about the limitations of the exemplar-based network, considering how the model might be further extended, and evaluating the model's applications.

[1]  J. Kruschke,et al.  ALCOVE: an exemplar-based connectionist model of category learning. , 1992, Psychological review.

[2]  R. Nosofsky.  Overall similarity and the identification of separable-dimension stimuli: A choice model analysis , 1985, Perception & psychophysics.

[3]  W. Estes.  Array models for category learning , 1986, Cognitive Psychology.

[4]  M. Gluck.  Stimulus Generalization and Representation in Adaptive Network Models of Category Learning , 1991 .

[5]  R. Nosofsky.  Attention, similarity, and the identification-categorization relationship. , 1986, Journal of experimental psychology. General.

[6]  M. Posner,et al.  On the genesis of abstract ideas. , 1968, Journal of experimental psychology.

[7]  R. Nosofsky.  Attention and learning processes in the identification and categorization of integral stimuli. , 1987, Journal of experimental psychology. Learning, memory, and cognition.

[8]  G. Chapman,et al.  Cue interaction in human contingency judgment , 1990, Memory & cognition.

[9]  W. R. Garner,et al.  Filtering and condensation tasks with integral and separable dimensions , 1975 .

[10]  G. Bower,et al.  Evaluating an adaptive network model of human learning , 1988 .

[11]  L. Hedges,et al.  Memory for day of the week: a 5 + 2 day cycle. , 1992, Journal of experimental psychology. General.

[12]  R. Nosofsky.  Similarity, frequency, and category representations. , 1988 .

[13]  M. Posner.  INFORMATION REDUCTION IN THE ANALYSIS OF SEQUENTIAL TASKS. , 1964, Psychological review.

[14]  Stephen K. Reed,et al.  Pattern recognition and categorization , 1972 .

[15]  R. Nosofsky.  Further tests of an exemplar-similarity approach to relating identification and categorization , 1989, Perception & psychophysics.

[16]  R. Nosofsky.  American Psychological Association, Inc. Choice, Similarity, and the Context Theory of Classification , 2022 .

[17]  M. Posner,et al.  Retention of Abstract Ideas. , 1970 .

[18]  D R Shanks,et al.  Connectionism and the Learning of Probabilistic Concepts , 1990, The Quarterly journal of experimental psychology. A, Human experimental psychology.

[19]  Douglas L. Medin,et al.  Context theory of classification learning. , 1978 .

[20]  Jerome R. Busemeyer,et al.  Resource allocation decision making in an uncertain environment , 1987 .

[21]  R. Shepard.  Stimulus and response generalization: tests of a model relating generalization to distance in psychological space. , 1958, Journal of experimental psychology.

[22]  Douglas L. Hintzman,et al.  "Schema Abstraction" in a Multiple-Trace Memory Model , 1986 .

[23]  R Ratcliff,et al.  Connectionist models of recognition memory: constraints imposed by learning and forgetting functions. , 1990, Psychological review.

[24]  Mark W. Altom,et al.  Correlated symptoms and simulated medical classification. , 1982, Journal of experimental psychology. Learning, memory, and cognition.

[25]  W. Estes,et al.  Base-rate effects in category learning: a comparison of parallel network and memory storage-retrieval models. , 1989, Journal of experimental psychology. Learning, memory, and cognition.

[26]  Gregory Ashby,et al.  Decision rules in the perception and categorization of multidimensional stimuli. , 1988, Journal of experimental psychology. Learning, memory, and cognition.

[27]  R. Rescorla,et al.  A theory of Pavlovian conditioning : Variations in the effectiveness of reinforcement and nonreinforcement , 1972 .

[28]  W. Estes,et al.  Toward a framework for combining connectionist and symbol-processing models☆ , 1988 .

[29]  R. Nosofsky.  Similarity Scaling and Cognitive Process Models , 1992 .

[30]  R. Shepard.  Stimulus and response generalization: deduction of the generalization gradient from a trace model. , 1958, Psychological review.

[31]  James L. McClelland.  Stochastic interactive processes and the effect of context on perception , 1991, Cognitive Psychology.

[32]  David R. Shanks,et al.  CATEGORIZATION BY A CONNECTIONIST NETWORK , 1991 .

[33]  M. Levine.  A cognitive theory of learning: Research on hypothesis testing. , 1975 .

[34]  R. Nosofsky,et al.  Rules and exemplars in categorization, identification, and recognition. , 1989, Journal of experimental psychology. Learning, memory, and cognition.

[35]  R. Shepard,et al.  Toward a universal law of generalization for psychological science. , 1987, Science.

[36]  W. R. Garner.  The Processing of Information and Structure , 1974 .

[37]  R. Shiffrin,et al.  List-strength Effect: Ii. Theoretical Mechanisms , 1990 .

[38]  D. Medin,et al.  Problem structure and the use of base-rate information from experience. , 1988, Journal of experimental psychology. General.

[39]  Robert M. Nosofsky,et al.  Exemplar-based approach to relating categorization, identification, and recognition , 1992 .

[40]  岡本 栄一,et al.  Tom Trabasso & Gardon H. Bower-Attention in Learning : Theory and Research., John Wiley and Sons, 1968, 234ページ , 1972 .

[41]  R. Nosofsky,et al.  Combining exemplar-based category representations and connectionist learning rules. , 1992, Journal of experimental psychology. Learning, memory, and cognition.

[42]  R. Nosofsky.  Exemplar-Based Accounts of Relations Between Classification, Recognition, and Typicality , 1988 .

[43]  R. Nosofsky.  Tests of an exemplar model for relating perceptual classification and recognition memory. , 1991, Journal of experimental psychology. Human perception and performance.

[44]  Liva Nohre,et al.  Instance Frequency, Categorization, and the Modulating Effect of Experience , 1991 .

[45]  R. Shepard,et al.  Learning and memorization of classifications. , 1961 .

[46]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[47]  D. Medin.  A theory of context in discrimination learning , 1975 .

[48]  R. Shepard,et al.  Stimulus generalization in the learning of classifications. , 1963, Journal of experimental psychology.

[49]  D. Homa.  On the Nature of Categories , 1984 .

[50]  G. Bower,et al.  From conditioning to category learning: an adaptive network model. , 1988 .