Pattern Recognition Statistical Structural And Neural

Explores the heart of pattern recognition concepts, methods and applications using statistical, syntactic and neural approaches. Divided into four sections, it clearly demonstrates the similarities and differences among the three approaches. The second part deals with the statistical pattern recognition approach, starting with a simple example and finishing with unsupervised learning through clustering. Section three discusses the syntactic approach and explores such topics as the capabilities of string grammars and parsing; higher dimensional representations and graphical approaches. Part four presents an excellent overview of the emerging neural approach including an examination of pattern associations and feedforward nets. Along with examples, each chapter provides the reader with pertinent literature for a more in-depth study of specific topics.

Robert J. Schalkoff is the author of Pattern Recognition: Statistical, Structural and Neural Approaches, published by Wiley.

STATISTICAL PATTERN RECOGNITION (StatPR).

Supervised Learning (Training) Using Parametric and Nonparametric Approaches.

Linear Discriminant Functions and the Discrete and Binary Feature Cases.

Unsupervised Learning and Clustering.

SYNTACTIC PATTERN RECOGNITION (SyntPR).

Overview.

Syntactic Recognition via Parsing and Other Grammars.

Graphical Approaches to SyntPR.

Learning via Grammatical Inference.

NEURAL PATTERN RECOGNITION (NeurPR).

Introduction to Neural Networks.

Introduction to Neural Pattern Associators and Matrix Approaches.

Feedforward Networks and Training by Backpropagation.

Content Addressable Memory Approaches and Unsupervised Learning in NeurPR.

Appendices.

References.

Permission Source Notes.

Index.