This paper describes NETtalk, a class of massively-parallel network systems that learn to convert English text to speech. The memory representations for pronunciations are learned by practice and are shared among many processing units. The performance of NETtalk has some similarities with observed human performance. (i) The learning follows a power law. (;i) The more words the network learns, the better it is at generalizing and correctly pronouncing new words, (iii) The performance of the network degrades very slowly as connections in the network are damaged: no single link or processing unit is essential. (iv) Relearning after damage is much faster than learning during the original training. (v) Distributed or spaced practice is more effective for long-term retention than massed practice. Network models can be constructed that have the same performance and learning characteristics on a particular task, but differ completely at the levels of synaptic strengths and single-unit responses. However, hierarchical clustering techniques applied to NETtalk reveal that these different networks have similar internal representations of letter-to-sound correspondences within groups of processing units. This suggests that invariant internal representations may be found in assemblies of neurons intermediate in size between highly localized and completely distributed representations.

A rational model of human categorization behavior is presented that assumes that categorization reflects the derivation of optimal estimates of the probability of unseen features of objects. A Bayesian analysis is performed of what optimal estimations would be if categories formed a disjoint partitioning of the object space and if features were independently displayed within a category. This Bayesian analysis is placed within an incremental categorization algorithm. The resulting rational model accounts for effects of central tendency of categories, effects of specific instances, learning of linearly nonseparable categories, effects of category labels, extraction of basic level categories, base-rate effects, probability matching in categorization, and trial-by-trial learning functions. Al-though the rational model considers just I level of categorization, it is shown how predictions can be enhanced by considering higher and lower levels. Considering prediction at the lower, individual level allows integration of this rational analysis of categorization with the earlier rational analysis of memory (Anderson & Milson, 1989). Anderson (1990) presented a rational analysis ot 6 human cog-nition. The term rational derives from similar "rational-man" analyses in economics. Rational analyses in other fields are sometimes called adaptationist analyses. Basically, they are ef-forts to explain the behavior in some domain on the assump-tion that the behavior is optimized with respect to some criteria of adaptive importance. This article begins with a general char-acterization ofhow one develops a rational theory of a particu-lar cognitive phenomenon. Then I present the basic theory of categorization developed in Anderson (1990) and review the applications from that book. Since the writing of the book, the theory has been greatly extended and applied to many new phenomena. Most of this article describes these new develop-ments and applications. A Rational Analysis Several theorists have promoted the idea that psychologists might understand human behavior by assuming it is adapted to the environment (e.g., Brunswik, 1956; Campbell, 1974; Gib-

the heuristics-and-biases approach to statistical reasoning is and is not about. At issue is the imposition of unnecessarily narrow norms of sound reasoning that are used to diagnose so-called cognitive illusions and the continuing reliance on vague heuristics that explain everything and nothing. D. Kahneman and A. Tversky (1996) incorrectly asserted that Gigerenzer simply claimed that frequency formats make all cognitive illusions disappear. In contrast, Gigerenzer has proposed and tested models that actually predict when frequency judgments are valid and when they are not. The issue is not whether or not. or how often, cognitive illusions disappear. The focus should be rather the construction of detailed models of cognitive processes that explain when and why they disappear. A postscript responds to Kahneman and Tversky's (1996) postscript. I welcome Kahneman and Tversky's (1996) reply to my critique (e.g., Gigerenzer, 1991, 1994; Gigerenzer & Murray, 1987) and hope this exchange will encourage a rethinking of research strategies. I emphasize research strategies, rather than specific empirical results or even explanations of those results, because I believe that this debate is fundamentally about what

SUSTAIN (Supervised and Unsupervised STratified Adaptive Incremental Network) is a model of how humans learn categories from examples. SUS-TAIN 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

Any agent in the real world has to be able to make distinctions between different types of objects, i.e. it must have the competence of categorization. In mobile agents, there is a large variation in proximal sensory stimulation originating from the same object. Therefore, categorization behavior is hard to achieve, and the successes in the past in solving this problem, have been limited. In this paper it is proposed that the problem of categorization in the real world is significantly simplified if it is viewed as one of sensory-motor coordination, rather than one of information processing happening "on the input side". A series of models is presented to illustrate the approach. It is concluded that we should consider replacing the metaphor of information processing for intelligent systems by the one of sensory-motor coordination. But the principle of sensory-motor coordination is more than a metaphor. It offers concrete mechanisms for putting agents to work in the real world. These i...

A connectionist model of argument strength is proposed that applies to categorical arguments involving natural categories and predicates about which subjects have few prior beliefs. An example is robins have sesamoid bones, therefore falcons have sesamoid bones. The model is based on the hypotheses that argument strength (i) increases with the overlap between features of the combined premise categories and features of the conclusion category; and (ii) decreases with the amount of prior knowledge about the conclusion category. The model assumes a two-stage process. First, premises are encoded by connecting the features of premise categories to the predicate. Second, conclusions are tested by examining the degree of activation of the predicate upon presentation of the features of the conclusion category. The model accounts for 13 qualitative phenomena and shows close quantitative fits to several sets of argument-strength ratings. Feature-based induction 3 3<E-2> One way we learn about ...

this article, we present a model of similarity comparison that makes specific time course predictions, which were tested in three experiments. Before turning to that model, we first outline the need for a consideration of similarity processes

Two connectionist models of attention in associative learning, previously used to model human category learning, are shown to have special cases that are essentially equivalent to N. J. Mackintosh's (1975, Psychological Review, 82, 276 298) classic model of attention in animal learning. The models unify formulas for associative weight change with formulas for attentional change, under a common goal of error reduction. Error-driven attentional shifting accelerates learning of new associations but also protects previously learned associations from retroactive interference. The models are fit to data from a recent experiment in human associative learning (J. K. Kruschke 6 N. J. Blair, 2000, Psychonomic Bulletin 6 Review, 7, 636 645), which shows that blocking of learning involves learned inattention. The approach also provides a novel and unifying theory of latent inhibition (the preexposure effect) in terms of blocking. The discussion summarizes how the approach accounts for a variety of other ``irrational' ' phenomena in associative learning, including base rate effects, perseveration of attention through relevance

On behalf of:

Adaptive network and exemplar-similarity models were compared on their ability to predict category learning and transfer data. An exemplar-based network (Kruschke, 1990a, 1990b, 1992) that combines key aspects of both modeling approaches was also tested. The exemplar-based network incorporates an exemplar-based category representation in which exemplars become associated to categories through the same error-driven, interactive learning rules that are assumed in standard adaptive networks. Experiment 1, which partially replicated and extended the probabilistic classification learning paradigm of Gluck and Bower (1988a), demonstrated the importance of an error-driven learning rule. Experiment 2, which extended the classification learning paradigm of Medin and Schaffer (1978) that discriminated between exemplar and prototype models, demonstrated the importance of an exemplar-based category representation. Only the exemplar-based network accounted for all the major qualitative phenomena; it also achieved good quantitative predictions of the learning and transfer data in both experiments. One of the major current models for explaining performance in arbitrary category learning paradigms is the context model proposed by Medin and Schaffer (1978) and elaborated by Estes (1986a) and Nosofsky (1984, 1986). According to the context model, people represent categories by storing individual exemplars in memory and make classification decisions on the basis of similarity comparisons with the stored exemplars. The context model has proved to be successful at predicting quantitative details of classification performance in a wide variety of experimental settings and has compared favorably with a variety of alternative models, including prototype, independent-feature, and certain logical-rule based models (see Medin & Florian, in press, and Nosofsky, in press-a, in press-b, for reviews). However, some shortcomings of the context model were recently demonstrated in series of probabilistic classification learning experiments conducted by Gluck and Bower (1988a)