Artificial neural networks and statistical pattern recognition: old and new connections
by Jain, Anil K. Sethi, Ishwar K.
With the growing complexity of pattern recognition related problems being solved using Artificial Neural Networks, many ANN researchers are grappling with design issues such as the size of the network, the number of training patterns, and performance assessment and bounds. These researchers are continually rediscovering that many learning procedures lack the scaling property; the procedures simply fail, or yield unsatisfactory results when applied to problems of bigger size. Phenomena like thes…
Read More ↓Title Statements
- Full title :Artificial neural networks and statistical pattern recognition : old and new connections / edited by Ishwar K. Sethi, Anil K. Jain.
Summary
With the growing complexity of pattern recognition related problems being solved using Artificial Neural Networks, many ANN researchers are grappling with design issues such as the size of the network, the number of training patterns, and performance assessment and bounds. These researchers are continually rediscovering that many learning procedures lack the scaling property; the procedures simply fail, or yield unsatisfactory results when applied to problems of bigger size. Phenomena like these are very familiar to researchers in statistical pattern recognition (SPR), where the <Q>curse of dimensionality</Q> is a well-known dilemma. Issues related to the training and test sample sizes, feature space dimensionality, and the discriminatory power of different classifier types have all been extensively studied in the SPR literature. It appears however that many ANN researchers looking at pattern recognition problems are not aware of the ties between their field and SPR, and are therefore unable to successfully exploit work that has already been done in SPR. Similarly, many pattern recognition and computer vision researchers do not realize the potential of the ANN approach to solve problems such as feature extraction, segmentation, and object recognition. The present volume is designed as a contribution to the greater interaction between the ANN and SPR research communities.
Read More ↓Edition Statements
- Publication Date:1991.
Publication Statements
- Publisher(s):Elsevier Science Pub. Co. [distributor], North-Holland
- Place of Publication:Amsterdam
- Language:eng
- Publication Date:1991.
The Physical Object
- Description:1 online resource (xiv, 271 pages) : : illustrations
Edition Identifiers
- ISBN:0444887407, 9780444887405, 9781483297873, 148329787X
- oclc:ocn645856210
- LC Classification:TK7882.P3
- Dewey Decimal:006.3
Table of Contents
Front Cover; Artificial Neural Networks and Statistical Pattern Recognition: Old and New Connections; Copyright Page; FOREWORD; PREFACE; Table of Contents; PART 1: ANN AND SPR RELATIONSHIP; CHAPTER 1. EVALUATION OF A CLASS OF PATTERN-RECOGNITION NETWORKS; INTRODUCTION; 1. A CLASS OF PATTERN-RECOGNITION NETWORKS; 2. A REPRESENTATION OF THE JOINT DISTRIBUTION; 3. A CLASS OF CLASSIFICATION FUNCTIONS; 4. DETERMINATION OF COEFFICIENTS FROM SAMPLES; 5. SOME COMMENTS ON COMPARING DESIGN PROCEDURES; 6. SOME COMMENTS ON THE CHOICE OF OBSERVABLES, AND ON INVARIANCE PROPERTIES; ACKNOWLEDGMENT
5. PEAKING IN THE CLASSIFICATION PERFORMANCE WITH INCREASE IN DIMENSIONALITY6. EFFECT OF THE NUMBER OF NEURONS IN THE HIDDEN LAYERON THE PERFORMANCE OF ANN CLASSIFIERS; 7. DISCUSSION; References; CHAPTER 4. On Tree Structured Classifiers; Abstract; 1. INTRODUCTION; 2. DECISION RULES AND CLASSIFICATION TREES; 3. CLASSIFICATION TREE CONSTRUCTION AND ERROR RATE ESTIMATION; 4. TREE PRUNING ALGORITHMS; 5. EXPERIMENTAL RESULTS; 6. CONCLUSION; REFERENCES; CHAPTER 5. Decision tree performance enhancement using an artificial neural network implementation; Abstract; 1. INTRODUCTION
2. DECISION TREE CLASSIFIER I…
Subjects
Writers
More from this Series
No reviews yet. Be the first to rate this work.
Related Works
more →
Zircon
Republicart practises: documentation, evaluation
A companion to literature and film
A companion to literature and film
Roman crossings: theory and practice in the Roman Republ…
Adaptationism and optimality
Didactics of mathematics as a scientific discipline
The Management challenge: Japanese views
Justification
Adaptationism and optimality
Micas
Pyroxenes
Virtue
Adaptationism and optimality
Adaptionism and optimality
Files & Downloads
-
Artificial neural networks and statistical patter…
DJVU · 9.9 MB · updated -
Artificial neural networks and statistical patter…
PDF · 19.0 MB · updated
Rate & Review