Map-Seeking Circuits in Visual Cognition: A Computational Mechanism for Biological and Machine Vision

by David W. Arathorn

Overview

This work presents a bold new theory of the cognitive circuitry of the brain, with emphasis on the functioning of human vision. Departing from conventional precepts in the fields of artificial intelligence, neuroscience, and visual psychophysics, the author has developed a computational theory that provides a unitary explanation for a wide range of visual capabilities and behaviors, most of which have no accepted theoretical explanation. He describes a cortical mechanism termed “map-seeking” and demonstrates its explanatory power in areas as diverse as limb-motion planning and perceptual deficits associated with schizophrenia.

The author argues that map-seeking is a fundamental, broadly applicable computational operation with algorithmic, neuronal, and analog electronic implementations, and that its generality makes it suitable as the core of a computational explanation for several cognitive functions. Variations of this map-seeking circuit perform recognition under visual transformations, tracking, scene segmentation, and determination of shape from view displacement.

The mathematical principle on which map-seeking depends, a superposition ordering property, solves the combinatorial explosion problem that has plagued all other approaches to visual computation. The author demonstrates that map-seeking is capable of realistic performances in neuronal form and in many current technological procedures. Because of its breadth of application, it is a plausible cortical theory. Because it can be implemented electronically, it forms the basis for a computational technology highly suited for visual, and other perceptual, cognitive, and motor applications.

Product Details

ISBN-13:	9780804742771
Publisher:	Stanford University Press
Publication date:	08/01/2002
Edition description:	1
Pages:	240
Product dimensions:	7.00(w) x 10.00(h) x 0.80(d)

About the Author

David W. Arathorn is an independent scholar whose principal work has been the design and implementation of large-scale industrial systems.

Table of Contents

	Figures	ix
	Foreword	xiii
	Preface	xvii
Chapter 1	Introduction to the Theory of Map-Seeking Circuits	1
1.1	Introduction
1.2	Map-Discovery in Vision
1.3	Context
1.4	Roots of the Theory
1.5	Scope and Organization
Chapter 2	The Algorithmic Map-Seeking Circuit	13
2.1	Relationship to the Theory
2.2	Elements of the Algorithmic Circuit
2.3	Behavior of Two Circuit Implementations
2.4	Multilayer Circuits
2.5	Other Multilayer Circuit Demonstrations
2.6	Convergence and the Ordering Property
2.7	Mapping Modes: Seeking, Driven, Restricted
Chapter 3	Shape Interpretation by Recharacterization	53
3.1	Shape Interpretation Mechanics
3.2	Geometry of Simple Terrain Angle Interpretation
3.3	Effective Extent of Mappings
3.4	Terrain Interpretation With Real Data
3.5	Determining Transverse Inclination, [theta]
3.6	The Need For a Viewpoint Independent 3D Model
3.7	Floating Patch Representation
3.8	Floating Patch Representation of Objects
Chapter 4	Unifying Vision and Kinematics	85
4.1	Grounding Vision
4.2	Forward and Inverse Kinematics by Map-Seeking Circuits
4.3	Other Sources of Visual Information
4.4	Terrain Vision Architecture
Chapter 5	Neuronal Map-Seeking Circuits	101
5.1	Characteristics of a Neuronal Implementation
5.2	Cell characteristics
5.3	The Cell Pair
5.4	Circuit Architecture
5.5	Circuit Dynamics
5.6	Collusion
5.7	Neuron Function: Idealized versus Biological
Chapter 6	Neuronal Circuit Behavior and Performance	123
6.1	Temporal Aspects of Circuit Performance
6.2	Input Encoding
6.3	Tracking a Target Moving Amid Clutter
6.4	Attention Shift Tests
6.5	Scene Segmentation
6.6	Repeated Pattern Recognition
6.7	Recharacterization with Repeated Patterns
6.8	Regularity Extraction in the Learning Process
Chapter 7	Neurophysiological, Psychophysical and Other Evidence	141
7.1	Purpose
7.2	Physiological Evidence
7.3	Psychophysical Evidence
7.4	Visual Deficits Associated with Schizophrenia
7.5	Repertoire of Transformations: Psychophysical Evidence
7.6	Recognition of Assembled Views
Chapter 8	Practical Map-Seeking Circuits and Map-Seeking Computers	171
8.1	Implications of a Map-Seeking Computing Technology
8.2	A Sense of Scale: Digital Implementation
8.3	Map-Seeking Computers
8.4	Analog Map-Seeking Circuit Implementations
Chapter 9	Related Issues and Lines of Future Research	179
9.1	A Taxonomy of "Recognition" Tasks
9.2	All very well, but...
9.3	The Main Concepts Revisited
9.4	Conclusion
	Appendices	189
	Bibliography	211
	Index	215

Editorial Reviews

What Arathorn has done is brilliant. The question of how the brain forms representations of objects which are invariant to changes in position, size, viewing angle, etc. is a deep and mysterious one, and he has come up with a clever solution based on remapping input patterns using a neural network. It provides the beginnings of a framework for thinking about visual cognition in neural terms, something that is sorely needed in the field.”—Bruno Olshausen, University of California, Davis

From the Publisher

An independent scholar, whose primary work has been in the design and implementation of large-scale industrial systems, presents a new theory to account for the brain's circuitry in visual capabilities (and deficits) based on a cognitive "map-seeking" mechanism. Arathorn argues that this algorithmic principle is also relevant to computing applications that are map-seeking rather than arithmetic-based, because it solves a major problem that has plagued other computational approaches to vision. Appendices cover such technical aspects as neuronal circuit simulation equations. Annotation c. Book News, Inc., Portland, OR