From Statistics to Neural Networks

This volume provides a unified approach to the study of predictive learning. It contains papers on major aspects of statistical and neural network learning, their links to biological learning and nonlinear dynamics (chaos), and real-life examples of pattern recognition applications.

Inhalt
An Overview of Predictive Learning and Function Approximation.- Nonparametric Regression and Classification Part I Nonparametric Regression.- Nonparametric Regression and Classification Part II Nonparametric Classification.- Neural Networks, Bayesian a posteriori Probabilities, and Pattern Classification.- Flexible Non-linear Approaches to Classification.- Parametric Statistical Estimation with Artificial Neural Networks: A Condensed Discussion.- Prediction Risk and Architecture Selection for Neural Networks.- Regularisation Theory, Radial Basis Functions and Networks.- Self-Organizing Networks for Nonparametric Regression.- Neural Preprocessing Methods.- Improved Hidden Markov Models for Speech Recognition Through Neural Network Learning.- Neural Network Architectures for Pattern Recognition.- Cooperative Decision Making Processes and Their Neural Net Implementation.- Associative Memory Networks and Sparse Similarity Preserving Codes.- Multistrategy Learning and Optimal Mappings.- Self-Organizing Neural Networks for Supervised and Unsupervised Learning and Prediction.- Recognition of 3-D Objects from Multiple 2-D Views by a Self-Organizing Neural Architecture.- Chaotic Dynamics in Neural Pattern Recognition.