Ebook: From Statistics to Neural Networks: Theory and Pattern Recognition Applications

The NATO Advanced Study Institute From Statistics to Neural Networks, Theory and Pattern Recognition Applications took place in Les Arcs, Bourg Saint Maurice, France, from June 21 through July 2, 1993. The meeting brought to­ gether over 100 participants (including 19 invited lecturers) from 20 countries. The invited lecturers whose contributions appear in this volume are: L. Almeida (INESC, Portugal), G. Carpenter (Boston, USA), V. Cherkassky (Minnesota, USA), F. Fogelman Soulie (LRI, France), W. Freeman (Berkeley, USA), J. Friedman (Stanford, USA), F. Girosi (MIT, USA and IRST, Italy), S. Grossberg (Boston, USA), T. Hastie (AT&T, USA), J. Kittler (Surrey, UK), R. Lippmann (MIT Lincoln Lab, USA), J. Moody (OGI, USA), G. Palm (U1m, Germany), B. Ripley (Oxford, UK), R. Tibshirani (Toronto, Canada), H. Wechsler (GMU, USA), C. Wellekens (Eurecom, France) and H. White (San Diego, USA). The ASI consisted of lectures overviewing major aspects of statistical and neural network learning, their links to biological learning and non-linear dynamics (chaos), and real-life examples of pattern recognition applications. As a result of lively interactions between the participants, the following topics emerged as major themes of the meeting: (1) Unified framework for the study of Predictive Learning in Statistics and Artificial Neural Networks (ANNs); (2) Differences and similarities between statistical and ANN methods for non­ parametric estimation from examples (learning); (3) Fundamental connections between artificial learning systems and biological learning systems.

---

This volume provides a unified approach to the study of predictive learning, i.e., generalization from examples. It contains an up-to-date review and in-depth treatment of major issues and methods related to predictive learning in statistics, Artificial Neural Networks (ANN), and pattern recognition. Topics range from theoretical modeling and adaptive computational methods to empirical comparisons between statistical and ANN methods, and applications. Most contributions fall into one of the three themes: unified framework for the study of predictive learning in statistics and ANNs; similarities and differences between statistical and ANN methods for nonparametric estimation (learning); and fundamental connections between artificial and biological learning systems.

---

This volume provides a unified approach to the study of predictive learning, i.e., generalization from examples. It contains an up-to-date review and in-depth treatment of major issues and methods related to predictive learning in statistics, Artificial Neural Networks (ANN), and pattern recognition. Topics range from theoretical modeling and adaptive computational methods to empirical comparisons between statistical and ANN methods, and applications. Most contributions fall into one of the three themes: unified framework for the study of predictive learning in statistics and ANNs; similarities and differences between statistical and ANN methods for nonparametric estimation (learning); and fundamental connections between artificial and biological learning systems.
Content:
Front Matter....Pages I-XII
An Overview of Predictive Learning and Function Approximation....Pages 1-61
Nonparametric Regression and Classification Part I—Nonparametric Regression....Pages 62-69
Nonparametric Regression and Classification Part II—Nonparametric Classification....Pages 70-82
Neural Networks, Bayesian a posteriori Probabilities, and Pattern Classification....Pages 83-104
Flexible Non-linear Approaches to Classification....Pages 105-126
Parametric Statistical Estimation with Artificial Neural Networks: A Condensed Discussion....Pages 127-146
Prediction Risk and Architecture Selection for Neural Networks....Pages 147-165
Regularization Theory, Radial Basis Functions and Networks....Pages 166-187
Self-Organizing Networks for Nonparametric Regression....Pages 188-212
Neural Preprocessing Methods....Pages 213-225
Improved Hidden Markov Models for Speech Recognition Through Neural Network Learning....Pages 226-242
Neural Network Architectures for Pattern Recognition....Pages 243-262
Cooperative Decision Making Processes and Their Neural Net Implementation....Pages 263-281
Associative Memory Networks and Sparse Similarity Preserving Codes....Pages 282-302
Multistrategy Learning and Optimal Mappings....Pages 303-318
Self-Organizing Neural Networks for Supervised and Unsupervised Learning and Prediction....Pages 319-348
Recognition of 3-D Objects from Multiple 2-D Views by a Self-Organizing Neural Architecture....Pages 349-375
Chaotic Dynamics in Neural Pattern Recognition....Pages 376-394
Back Matter....Pages 395-401

---

This volume provides a unified approach to the study of predictive learning, i.e., generalization from examples. It contains an up-to-date review and in-depth treatment of major issues and methods related to predictive learning in statistics, Artificial Neural Networks (ANN), and pattern recognition. Topics range from theoretical modeling and adaptive computational methods to empirical comparisons between statistical and ANN methods, and applications. Most contributions fall into one of the three themes: unified framework for the study of predictive learning in statistics and ANNs; similarities and differences between statistical and ANN methods for nonparametric estimation (learning); and fundamental connections between artificial and biological learning systems.
Content:
Front Matter....Pages I-XII
An Overview of Predictive Learning and Function Approximation....Pages 1-61
Nonparametric Regression and Classification Part I—Nonparametric Regression....Pages 62-69
Nonparametric Regression and Classification Part II—Nonparametric Classification....Pages 70-82
Neural Networks, Bayesian a posteriori Probabilities, and Pattern Classification....Pages 83-104
Flexible Non-linear Approaches to Classification....Pages 105-126
Parametric Statistical Estimation with Artificial Neural Networks: A Condensed Discussion....Pages 127-146
Prediction Risk and Architecture Selection for Neural Networks....Pages 147-165
Regularization Theory, Radial Basis Functions and Networks....Pages 166-187
Self-Organizing Networks for Nonparametric Regression....Pages 188-212
Neural Preprocessing Methods....Pages 213-225
Improved Hidden Markov Models for Speech Recognition Through Neural Network Learning....Pages 226-242
Neural Network Architectures for Pattern Recognition....Pages 243-262
Cooperative Decision Making Processes and Their Neural Net Implementation....Pages 263-281
Associative Memory Networks and Sparse Similarity Preserving Codes....Pages 282-302
Multistrategy Learning and Optimal Mappings....Pages 303-318
Self-Organizing Neural Networks for Supervised and Unsupervised Learning and Prediction....Pages 319-348
Recognition of 3-D Objects from Multiple 2-D Views by a Self-Organizing Neural Architecture....Pages 349-375
Chaotic Dynamics in Neural Pattern Recognition....Pages 376-394
Back Matter....Pages 395-401
....