Neural Networks and Pattern Recognition

Omid Omidvar, Judith Dayhoff

• Publisher: Academic Press
• Year: 1997
• Print ISBN: 9780125264204
• eBook ISBN: 9780080512617
• Topic: Biological Sciences
• Subtopic: Zoology
• Index: Biological Sciences

This book is one of the most up-to-date and cutting-edge texts available on the rapidly growing application area of neural networks. Neural Networks and Pattern Recognition focuses on the use of neural networksin pattern recognition, a very important application area for neural networks technology. The contributors are widely known and highly respected researchers and practitioners in the field. - Features neural network architectures on the cutting edge of neural network research - Brings together highly innovative ideas on dynamical neural networks - Includes articles written by authors prominent in the neural networks research community - Provides an authoritative, technically correct presentation of each specific technical area

Chapter 1

Pulse-Coupled Neural Networks

J.L. Johnson; H. Ranganath; G. Kuntimad; H.J. Caulfield

ABSTRACT

A pulse-coupled neural network using the Eckhorn linking field coupling [1] is shown to contain invariant spatial information in the phase structure of the output pulse trains. The time domain signals axe directly related to the intensity histogram of an input spatial distribution and have complex phase factors that specify the spatial location of the histogram elements. Two time scales are identified. On the fast time scale the linking produces dynamic, quasi-periodic, fringe-like traveling waves [2] that can carry information beyond the physical limits of the receptive fields. These waves contain the morphological connectivity structure of image elements. The slow time scale is set by the pulse generator, and on that scale the image is segmented into multineuron time-synchronous groups. These groups act as giant neurons, firing together, and by the same linking field mechanism as for the linking waves can form quasi-periodic pulse structures whose relative phases encode the location of the groups with respect to one another. These time signals are a unique, object-specific, and roughly invariant time signature for their corresponding input spatial image or distribution [3].

The details of the model are discussed, giving the basic Eckhorn linking field, extensions, generation of time series in the limit of very weak linking, invariances from the symmetries of the receptive fields, time scales, waves, and signatures. Multirule logical systems are shown to exist on single neurons. Adaptation is discussed. The pulse-coupled nets are compatible with standard nonpulsed adaptive nets rather than competitive with them in the sense that any learning law can be used. Their temporal nature results in adaptive associations in time as well as over space, and they are similar to the time-sequence learning models of Reiss and Taylor [4]. Hardware implementations, optical and electronic, are reviewed. Segmentation, object identification, and location methods are discussed and current results given. The conjugate basic problem of transforming a time signal into a spatial distribution, comparable in importance to the transformation of a spatial distribution into a time signal, is discussed. It maps the invariant time signature into a phase versus frequency spatial distribution and is the spatial representation of the complex histogram. A method of generating this map is discussed. Image pattern recognition using this network is shown to have the power of syntactical pattern recognition and the simplicity of statistical pattern recognition.

1 Introduction

The linking field model of Eckhorn et al. [1] was proposed as a minimal model to explain the experimentally observed synchronous feature-dependent activity of neural assemblies over large cortical distances in the cat cortex [5]. It is a cortical model. It emphasizes synchronizations of oscillatory spindles that occur in the limit of strong linking fields and distinguishes two major types: (1) forced, or stimulus-locked, synchronous activity and (2) induced synchronous activity. Forced activity is produced by abrupt temporal changes such as movement. Induced activity occurs when the pulse train structure of the outputs of groups of cells are similar [6]. The model is called “linking field” because it uses a secondary receptive field’s input to modulate a primary receptive field’s input by multiplication in order to obtain the necessary coupling that links the pulse activity into synchronicity.

This paper is concerned with the behavior of the linking field model in the limit of weak-to-moderate linking strengths [2],[7]. Strong linking is characterized by synchronous bursts of pulses. When the linking strength is reduced, the neurons no longer fire in bursts but still have a high degree of phase and frequency locking. This is the regime of moderate linking strength. Further reduction continuously lowers the degree of linking to a situation where locking can occur only for small phase and frequency differences. This is the weak linking regime. A major result of this research is the finding that in the weak linking regime it is possible to encode spatial input distributions into corresponding temporal patterns with enough structure...

Table of contents

• Cover image
• Title page
• Table of Contents
• Copyright page
• Preface
• Contributors
• Chapter 1: Pulse-Coupled Neural Networks
• Chapter 2: A Neural Network Model for Optical Flow Computation
• Chapter 3: Temporal Pattern Matching Using an Artificial Neural Network
• Chapter 4: Patterns of Dynamic Activity and Timing in Neural Network Processing
• Chapter 5: A Macroscopic Model of Oscillation in Ensembles of Inhibitory and Excitatory Neurons
• Chapter 6: Finite State Machines and Recurrent Neural Networks — Automata and Dynamical Systems Approaches
• Chapter 7: Biased Random-Walk Learning: A Neurobiological Correlate to Trial-and-Error
• Chapter 8: Using SONNET 1 to Segment Continuous Sequences of Items
• Chapter 9: On the Use of High-Level Petri Nets in the Modeling of Biological Neural Networks
• Chapter 10: Locally Recurrent Networks: The Gamma Operator, Properties, and Extensions
• Index