Connectionist Models In Cognitive Psychology

Connectionist Models in Cognitive Psychology is a state-of-the-art review of neural network modelling in core areas of cognitive psychology including: memory and learning, language (written and spoken), cognitive development, cognitive control, attention and action. The chapters discuss neural network models in a clear and accessible style, with an emphasis on the relationship between the models and relevant experimental data drawn from experimental psychology, neuropsychology and cognitive neuroscience. These lucid high-level contributions will serve as introductory articles for postgraduates and researchers whilst being of great use to undergraduates with an interest in the area of connectionist modelling.

A state-of-the-art review of neural network modelling in core areas of cognitive psychology including: memory and learning, language (written and spoken), cognitive development, cognitive control, attention and action.

Connectionist modelling and neural network applications had become a major sub-field of cognitive science by the mid-1990s. In this ground-breaking book, originally published in 1995, leading connectionists shed light on current approaches to memory and language modelling at the time. The book is divided into four sections: Memory; Reading; Computation and statistics; Speech and audition. Each section is introduced and set in context by the editors, allowing a wide range of language and memory issues to be addressed in one volume. This authoritative advanced level book will still be of interest for all engaged in connectionist research and the related areas of cognitive science concerned with language and memory.

This textbook provides an introduction and review of connectionist models applied to psychological topics. Chapters include basic reviews of connectionist models, their properties and their attributes. The application of these models to the domains of perception, memory, attention, word processing, higher language processing, and cognitive neuropsychology is then reviewed.

This title presents the most comprehensive existing "case study" of how the effects of damage in connectionist models can replicate the patterns of cognitive impairments that can arise in humans as a result of brain damage.

Although neural network models have had a dramatic impact on the cognitive and brain sciences, social psychology has remained largely unaffected by this intellectual explosion. The first to apply neural network models to social phenomena, this book includes chapters by nearly all of the individuals currently working in this area. Bringing these various approaches together in one place, it allows readers to appreciate the breadth of these approaches, as well as the theoretical commonality of many of these models. The contributors address a number of central issues in social psychology and show how these kinds of models provide insight into many classic issues. Many chapters hint that this approach provides the seeds of a theoretical integration that the field has lacked. Each chapter discusses an explicit connectionist model of a central problem in social psychology. Since many of the contributors either use a standard architecture or provide a computer program, interested readers, with a little work, should be able to implement their own variations of models. Chapters are devoted to the following topics and models: * the learning and application of social categories and stereotypes; * causal reasoning, social explanation, and person perception; * personality and social behavior; * classic dissonance phenomena; and * belief change and the coherence of large scale belief systems.

A cutting-edge reference source for the interdisciplinary field of computational cognitive modeling.

This volume provides an overview of a relatively neglected branch of connectionism known as localist connectionism. The singling out of localist connectionism is motivated by the fact that some critical modeling strategies have been more readily applied in the development and testing of localist as opposed to distributed connectionist models (models using distributed hidden-unit representations and trained with a particular learning algorithm, typically back-propagation). One major theme emerging from this book is that localist connectionism currently provides an interesting means of evolving from verbal-boxological models of human cognition to computer-implemented algorithmic models. The other central messages conveyed are that the highly delicate issue of model testing, evaluation, and selection must be taken seriously, and that model-builders of the localist connectionist family have already shown exemplary steps in this direction.