Karen van Hoek presents a cogent analysis of the classic problem of constraints on pronominal anaphora within the framework of Cognitive Grammar. Van Hoek proceeds from the position that grammatical structure can be characterized in terms of semantic and phonological representations, without autonomous syntactic structures or principles such as tree structures or c-command. She argues that constraints on anaphora can be explained in terms of semantic interactions between nominals and the contexts in which they are embedded.

Integrating the results of previous work, Van Hoek develops a model in which some nominals function as "conceptual reference points" that dominate over stretches defined by the semantic relations among elements. When a full noun is in the domain of a reference point, coreference is ruled out, since the speaker would be sending contradictory messages about the salience of the noun's referent.

With profound implications for the nature of syntax, this book will interest theoretical linguists of all persuasions.

The rapid growth of neural network research has led to a major reappraisal of many fundamental assumptions in cognitive and perceptual psychology. This text—aimed at the advanced undergraduate and beginning postgraduate student—is an in-depth guide to those aspects of neural network research that are of direct relevance to human information processing.

Examples of new connectionist models of learning, vision, language and thought are described in detail. Both neurological and psychological considerations are used in assessing its theoretical contributions. The status of the basic predicates like exclusive-OR is examined, the limitations of perceptrons are explained and properties of multi-layer networks are described in terms of many examples of psychological processes. The history of neural networks is discussed from a psychological perspective which examines why certain issues have become important. The book ends with a general critique of the new connectionist approach.

It is clear that new connectionism work provides a distinctive framework for thinking about central questions in cognition and perception. This new textbook provides a clear and useful introduction to its theories and applications.

While neuroscientists garner success in identifying brain regions and in analyzing individual neurons, ground is still being broken at the intermediate scale of understanding how neurons combine to encode information. This book proposes a method of representing information in a computer that would be suited for modeling the brain's methods of processing information.

Holographic Reduced Representations (HRRs) are introduced here to model how the brain distributes each piece of information among thousands of neurons. It had been previously thought that the grammatical structure of a language cannot be encoded practically in a distributed representation, but HRRs can overcome the problems of earlier proposals. Thus this work has implications for psychology, neuroscience, linguistics, and computer science, and engineering.