haracterized by descriptions of each module and how each serves in those tasks for which it is best suited. However, these theories often do not emphasize how modules interact in producing responses and in learning. In this article we will develop a modular theory of categorization that follows from two distinct accounts of this behavior. The first account is that of rule-based theories of categorization. These theories emerge from a philosophical tradition in which concepts and categorization are described in terms of definitional rules. For example, if a living thing has a wide, flat tail and constructs dams by cutting down trees with its This work was supported by Indiana University Cognitive Science Program Fellowships and by NIMH ResearchTraining Grant PHS-T32-MH19879-03 to Erickson, and in part by NIMH FIRST Award 1-R29-MH51572-01 to Kruschke. This research was reported as a poster at the 1996 Cognitive Science Society Conference in San Diego, CA. We than

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

Abstract not found

Category learning is often seen as a process of inductive generalization from a set of class-labeled exemplars. Human learners, however, often receive direct instruction concerning the structure of a category before being presented with examples. Such explicit knowledge may often be smoothly integrated with knowledge garnered by exposure to instances, but some interference effects have been observed. Specifically, errors in instructed rule following may sometimes arise after the repeated presentation of correctly labeled exemplars. Despite perfect consistency between instance labels and the provided rule, such inductive training can drive categorization behavior away from rule following and towards a more prototype-based or instance-based pattern. In this paper we present a general connectionist model of instructed category learning which captures this kind of interference effect. We model instruction as a sequence of inputs to a network which transforms such advice into a modulating f...

The authors present 2 experiments that establish the presence of knowledge partitioning in perceptual categorization. Many participants learned to rely on a context cue, which did not predict category membership but identified partial boundaries, to gate independent partial categorization strategies. When participants partitioned their knowledge, a strategy used in 1 context was unaffected by knowledge demonstrably present in other contexts. An exemplar model, attentional learning covering map, was shown to be unable to accommodate knowledge partitioning. Instead, a mixture-of-experts model, attention to rules and instances in a unified model (ATRIUM), could handle the results. The success of ATRIUM resulted from its assumption that people memorize not only exemplars but also the way in which they are to be classified. In this article, we address the representation of complex perceptual categories. Contrary to the conventional and widespread assumption that people’s representations are homogeneous and integrated, we show in two experiments that people often master a complex categorization task by forming independent components, or parcels, of knowledge. We also show that once a knowledge

Abstract not found

Proposed is GLLL2, a hybrid architecture of a global and a local learning module, which learns default and exceptional knowledge respectively from noisy examples. The global learning module, which is a feedforward neural network, captures global trends gradually, while the local learning module stores local exceptions quickly. The latter module distinguishes noise from exceptions, and learns only exceptions, which ability makes GLLL2 noise-tolerant. The results of experiments show the process in which training examples are formed into default and exceptional knowledge, and demonstrate that the predictive accuracy, the space efficiency, and the training efficiency of GLLL2 is higher than those of each individual module. Introduction In cognitive science, whether learners induce rules or remember exemplars has been at issue recently. In particular, learning processes of quasi-regular tasks that involve both regularities and exceptions has attracted considerable attention. We developed G...

Numeracy is regarded as an emergent property of the human brain, suggesting that neural network based simulations may provide some insight into the “cerebral substrate” used in operations related to numeracy. Two operations, subitization – the so-called phenomenon of the discrimination of visual number – and counting – a recurrent operation – have been studied within a multi-net framework. A multi-net architecture comprising unsupervised networks has been developed which successfully simulates aspects of subitization, especially when compared to similar work using supervised learning algorithms. Another multi-net architecture comprising unsupervised networks, and a recurrent backpropagation network, appears to learn numerosity and successfully simulates errors children make when they are learning to count. The systems for subitizing and counting were incorporated into a gated multi-net system for simulating the dual existence of both subitization and counting. Multi-net architectures provide a good basis for studying the emergent properties of an intelligent system in that a single monolithic network may be used to fit almost any data available.