this book provides an overview of pattern recognition and neural networks, covering a wide range of topics in statistical decision theory, linear discriminant analysis, flexible discriminants, feed-forward neural networks, non-parametric methods, tree-structured classifiers, belief networks, and unsupervised methods. it also discusses feature extraction and statistical methods for estimation and optimization. the book is structured into ten chapters, each focusing on different aspects of pattern recognition and neural networks. the first chapter introduces the concepts and provides examples. the second chapter covers statistical decision theory, including bayes rules, parametric models, and logistic discrimination. the third chapter discusses linear discriminant analysis, including classical methods and robustness. the fourth chapter explores flexible discriminants, including smooth parametric functions and regularization. the fifth chapter focuses on feed-forward neural networks, including their biological motivation, theory, and learning algorithms. the sixth chapter covers non-parametric methods, including density estimation and nearest neighbor methods. the seventh chapter discusses tree-structured classifiers, including splitting and pruning rules. the eighth chapter covers belief networks, including graphical models and causal networks. the ninth chapter discusses unsupervised methods, including projection methods and clustering algorithms. the tenth chapter focuses on finding good pattern features, including bounds for the bayes error and feature extraction techniques. the book also includes appendices on statistical methods, glossary, references, and author and subject indexes.this book provides an overview of pattern recognition and neural networks, covering a wide range of topics in statistical decision theory, linear discriminant analysis, flexible discriminants, feed-forward neural networks, non-parametric methods, tree-structured classifiers, belief networks, and unsupervised methods. it also discusses feature extraction and statistical methods for estimation and optimization. the book is structured into ten chapters, each focusing on different aspects of pattern recognition and neural networks. the first chapter introduces the concepts and provides examples. the second chapter covers statistical decision theory, including bayes rules, parametric models, and logistic discrimination. the third chapter discusses linear discriminant analysis, including classical methods and robustness. the fourth chapter explores flexible discriminants, including smooth parametric functions and regularization. the fifth chapter focuses on feed-forward neural networks, including their biological motivation, theory, and learning algorithms. the sixth chapter covers non-parametric methods, including density estimation and nearest neighbor methods. the seventh chapter discusses tree-structured classifiers, including splitting and pruning rules. the eighth chapter covers belief networks, including graphical models and causal networks. the ninth chapter discusses unsupervised methods, including projection methods and clustering algorithms. the tenth chapter focuses on finding good pattern features, including bounds for the bayes error and feature extraction techniques. the book also includes appendices on statistical methods, glossary, references, and author and subject indexes.