3rd Edition

Introduction to Neural and Cognitive Modeling 3rd Edition

By Daniel S. Levine Copyright 2019
    480 Pages
    by Routledge

    480 Pages
    by Routledge

    This textbook provides a general introduction to the field of neural networks. Thoroughly revised and updated from the previous editions of 1991 and 2000, the current edition concentrates on networks for modeling brain processes involved in cognitive and behavioral functions. Part one explores the philosophy of modeling and the field’s history starting from the mid-1940s, and then discusses past models of associative learning and of short-term memory that provide building blocks for more complex recent models. Part two of the book reviews recent experimental findings in cognitive neuroscience and discusses models of conditioning, categorization, category learning, vision, visual attention, sequence learning, behavioral control, decision making, reasoning, and creativity. The book presents these models both as abstract ideas and through examples and concrete data for specific brain regions.

    The book includes two appendices to help ground the reader: one reviewing the mathematics used in network modeling, and a second reviewing basic neuroscience at both the neuron and brain region level. The book also includes equations, practice exercises, and thought experiments.

    Contents

     

    Part I: Foundations of Neural Network Theory

    Chapter 1: Neural Networks for Modeling Behavior

    Chapter 2: Historical Outline

    Chapter 3: Associative Learning and Synaptic Plasticity

    Chapter 4: Competition, Lateral Inhibition, and Short-Term Memory

    Part II: Computational Cognitive Neuroscience

    Chapter 5: Progress in Cognitive Neuroscience

    Chapter 6: Models of Conditioning and Reinforcement Learning

    Chapter 7: Models of Coding, Categorization, and Unsupervised Learning

    Chapter 8: Models of Supervised Pattern and Category Learning

    Chapter 9: Models of Complex Mental Functions

    Appendices

    Appendix 1: Mathematical Techniques for Neural Networks

    Appendix 2: Basic Facts of Neurobiology

    References

    Biography

    Daniel S. Levine is Professor of Psychology at the University of Texas at Arlington. He is a Fellow and former President of the International Neural Network Society. His research involves computational modeling of brain processes in decision making and cognitive-emotional interactions.

    ‘Newly updated with advances in cognitive neuroscience and modeling, this introductory textbook provides a remarkable overview of the whole field of neural and cognitive modeling, from its inception nearly a century ago to the most recent advances. The beginner can easily gain an overview of the principles of modeling, while the advanced student will find ample mathematical detail and practical simulation exercises. This new edition will be my go-to text for advanced undergraduates and graduate students looking for an introduction to the subject.’ Professor Joshua W. Brown, Indiana University, USA

    ‘Levine's book achieves an impressive synthesis of historical trends and current research results in both biological and artificial neural network research. This synthesis clarifies that the currently popular Deep Learning is just one contribution to this burgeoning field, and one that does not incorporate many of the most powerful properties of biological learning. Levine's book provides an accessible introduction to many of these properties, while also reviewing important properties of neural models of vision and visual attention, sequence learning and performance, executive function, and decision-making, among its other expository accomplishments.’ Stephen Grossberg, Boston University, USA