In the past, nearest neighbor algorithms for learning from examples have worked best in domains in which all features had numeric values. In such domains, the examples can be treated as points and distance metrics can use standard definitions. In symbolic domains, a more sophisticated treatment of the feature space is required. We introduce a nearest neighbor algorithm for learning in domains with symbolic features. Our algorithm calculates distance tables that allow it to produce real-valued distances between instances, and attaches weights to the instances to further modify the structure of feature space. We show that this technique produces excellent classification accuracy on three problems that have been studied by machine learning researchers: predicting protein secondary structure, identifying DNA promoter sequences, and pronouncing English text. Direct experimental comparisons with the other learning algorithms show that our nearest neighbor algorithm is comparable or superior ...

Humans routinely generalize universal relationships to unfamiliar instances. If we are told ‘‘if glork then frum,’ ’ and ‘‘glork,’ ’ we can infer ‘‘frum’’; any name that serves as the subject of a sentence can appear as the object of a sentence. These universals are pervasive in language and reasoning. One account of how they are generalized holds that humans possess mechanisms that manipulate symbols and variables; an alternative account holds that symbol-manipulation can be eliminated from scientific theories in favor of descriptions couched in terms of networks of interconnected nodes. Can these ‘‘eliminative’ ’ connectionist models offer a genuine alternative? This article shows that eliminative connectionist models cannot account for how we extend universals to arbitrary items. The argument runs as follows. First, if these models, as currently conceived, were to extend universals to arbitrary instances, they would have to generalize outside the space of training examples. Next, it is shown that the class of eliminative connectionist models that is currently popular cannot learn to extend universals outside the training space. This limitation might be avoided through the use of an architecture that implements symbol manipulation.

. This paper describes an approach that uses interactive computer games as an experimental setting for the study of emotion, behavior, and nonverbal communication. In the first, more technical part, we present a method that allows to automatically code facial behavior of a subject playing a computer game. In this procedure, facial behavior is registered automatically with the aid of small plastic dots which are affixed to pre-defined regions of the subjects face. The resulting dot patterns are then classified with an artificial neural network. In the second part of the article, we discuss the theoretical framework of our experimental approach. In this view, the computer game provides a relatively simple but complete context - a microworld in the sense of Toda's 'Fungus Eater' - for the interpretation of the internal emotional and cognitive regulatory processes. In the third part, we contrast the empirical work with a synthetic approach where we can use the theoretical assumptions and t...

Twelve participants were trained to be experts at identifying a set of `Greebles', novel objects that, like faces, all share a common spatial configuration. Tests comparing expert with novice performance revealed: (1) a surprising mix of generalizability and specificity in expert object recognition processes; and (2) that expertise is a multi-faceted phenomenon, neither adequately described by a single term nor adequately assessed by a single task. Greeble recognition by a simple neural-network model is also evaluated, and the model is found to account surprisingly well for both generalization and individuation using a single set of processes and representations. 1998 Elsevier Science Ltd. All rights reserved. Keywords: Configural encoding; Face recognition; Neural networks; Object categorization; Perceptual expertise 1. Introduction Are the mechanisms used by perceivers as they become increasingly familiar with an object class the same as those used by perceivers when they first en...

Subjects exposed to strings of letters generated by a finite state grammar can later classify grammatical and nongrammatical test strings, even though they cannot adequately say what the rules of the grammar are (e.g., Reber, 1989). The MINERVA 2 (Hintzman, 1986) and Medin and Schaffer (1978) memory-array models and a number of connectionis? autoassociator models are tested against experimental data by derlving mainly parameter-free predictions from the models of the rank order of classification difficulty of test strings. The importance of different assumptions regarding the coding of features (How should the absence of a feature be coded? Should single letters or digrams be coded?), the learning rule used (Hebb rule vs. delta rule), and the connectivity (Should features be predicted only by previous features in the string, or by all features simultaneously?) is investigated by determlning the performance of the models with and without each assumption. Only one class of connectionist model (the simultaneous delta rule) passes all the tests. I? is shown that this class of model can be regarded by abstracting a se? of representative but incomplete rules of the grammar. Recently, there has been considerable interest in how subjects learn artificial

Human episodic memory provides a seemingly unlimited storage for everyday experiences, and a retrieval system that allows us to access the experiences with partial activation of their components. The system is believed to consist of a fast, temporary storage in the hippocampus, and a slow, longterm storage within the neocortex. This paper presents a neural network model of the hippocampal episodic memory inspired by Damasio's idea of Convergence Zones. The model consists of a layer of perceptual feature maps and a binding layer. A perceptual feature pattern is coarse coded in the binding layer, and stored on the weights between layers. A partial activation of the stored features activates the binding pattern, which in turn reactivates the entire stored pattern. For many configurations of the model, a theoretical lower bound for the memory capacity can be derived, and it can be an order of magnitude or higher than the number of all units in the model, and several orders of magnitude higher than the number of binding-layer units. Computational simulations further indicate that the average capacity is an order of magnitude larger than the theoretical lower bound, and making the connectivity between layers sparser causes an even further increase in capacity. Simulations also show that if more descriptive binding patterns are used, the errors tend to be more plausible (patterns are confused with other similar patterns), with a slight cost in capacity. The convergence-zone episodic memory therefore accounts for the immediate storage and associative retrieval capability and large capacity of the hippocampal memory, and shows why the memory encoding areas can be much smaller than the perceptual maps, consist of rather coarse computational units, and be only sparsely connected t...

There is a great deal of interest in characterizing the representations and processes that support visual word priming and written word identification more generally. On one view, these phenomena are supported by abstract orthographic representations that map together visually dissimilar exemplars of letters and words (e.g., the letters A/a map onto a common abstract letter code a*). On a second view, orthographic codes consist in a collection of episodic representations of words that interact in such a way that it sometimes looks as if there are abstract codes. P.L. Tenpenny (1995) contrasted these general approaches, and concluded by endorsing the episodic account, arguing that no evidence demands that we posit abstract orthographic representations. This review re-considers the evidence, and argues that a variety of priming and non-priming research strongly supports the conclusion that abstract orthographic codes exist and support priming and word identification. On this account, episodic representations are represented separately from abstract orthographic knowledge, and contribute minimally to these functions. In defense of abstractionist theories of repetition priming and word identification There is a great deal of interest in characterizing the representations and processes that support the improved processing of stimuli repeated during an experiment; the so-called repetition priming effect. Indeed, two different types of repetition priming have been intensively studied from two quite different perspectives. On the one hand, researchers interested in memory have tended to focus on long-term repetition priming, in which facilitation can last minutes, hours, and sometimes longer (Sloman, Hayman, Ohta, Law, & Tulving, 1988). For example, participants are generally f...

This thesis addresses a set of problems faced by connectionist learning that have originated from the observation that connectionist cognitive models lack two fundamental properties of the mind: Generativity, stemming from the boundless cognitive competence one can exhibit, and systematicity, due to the existence of symmetries within them. Such properties have seldom been seen in neural networks models, which have typically suffered from problems of inadequate generalization, as examplified both by small number of generalizations relative to training set sizes and heavy interference between newly learned items and previously learned information. Symbolic theories, arguing that mental representations have syntactic and semantic structure built from structured combinations of symbolic constituents, can in principle account for these properties (both arise from the sensitivity of structured semantic content with a generative and systematic syntax). This thesis studies the question of whe...

The views, opinions, and findings contained in this report are those of the authors and should not be construed as an official Department of the Army position, policy, or decision, unless so designated by other official documentation ACKNOWLEDGMENTS We are grateful to Dr. Jon Fallesen of ARI for his advice and support throughout the preparation of this report. We also appreciate the comments and feedback of many others at the Fort Leavenworth ARI Field Unit. We wish to thank Captain Clay Miller for his work arranging our visits to four different Army posts. And we are especially grateful to the many officers who agreed to serve as subjects. Finally, thanks to General Leonard P. Wishart, III, USA (ret.) and General Charles P. Otstott, USA (ret.) for their invaluable advice at various stages of the project. A COGNITIVE FRAMEWORK FOR BATTLEFIELD COMMANDERS ' SITUATION ASSESSMENT

Major biases and stereotypes in group judgments are reviewed and modeled from a recurrent connectionist perspective. These biases are in the areas of group impression formation (illusory correlation), group differentiation (accentuation), stereotype change (dispersed vs. concentrated distribution of inconsistent information), and group homogeneity. All these phenomena are illustrated with well-known experiments, and simulated with an autoassociative network architecture with linear activation update and delta learning algorithm for adjusting the connection weights. All the biases were successfully reproduced in the simulations. The discussion centers on how the particular simulation specifications compare with other models of group biases and how they may be used to develop novel hypotheses for testing the connectionist modeling approach and, more generally, for improving theorizing in the field of social biases and stereotype change. Petite, attractive, intelligent, WSF, 30, fond of music, theatre, books, travel, seeks warm, affectionate, fun-loving man to share life’s pleasures with view to lasting relationship. Send photograph. Please no