Kooperativer Bibliotheksverbund

UID:

Format: XIV, 271 S. : Ill., graph. Darst.

ISBN: 0-444-88740-7 , 0-444-88741-5

Series Statement: Machine intelligence and pattern recognition 11

Note: Literaturangaben

Language: English

Subjects: Computer Science

Keywords: Mustererkennung ; Neuronales Netz ; Aufsatzsammlung ; Aufsatzsammlung ; Aufsatzsammlung

URL: http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=002978630&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA

URL: Inhaltsverzeichnis

URL: http://bvbr.bib-bvb.de:8991/F?func=service&doc_library=BVB01&local_base=BVB01&doc_number=002978630&sequence=000002&line_number=0001&func_code=DB_RECORDS&service_type=MEDIA

UID:

Format: 1 online resource (286 p.)

ISBN: 1-4832-9787-X

Series Statement: Machine Intelligence and Pattern Recognition ; Volume 11

Content: 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 curse of dimen

Note: Description based upon print version of record. , 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 , REFERENCESCHAPTER 2. LINKS BETWEEN ARTIFICIAL NEURAL NETWORKS (ANN) AND STATISTICAL PATTERN RECOGNITION; 1. Overview; 2. Neural Networks and Pattern Recognition - ̨Generalities; 3. Some Examples of ANN Paradigms; 4. Dynamic Systems and Control; 5. Conclusions; REFERENCES; CHAPTER 3. Small sample size problems in designing artificial neural networks; Abstract; 1. INTRODUCTION; 2. FINITE SAMPLE PROBLEMS IN STATISTICAL PATTERN RECOGNITION; 3. THE CLASSIFICATION ACCURACY AND TRAINING TIME OF ARTIFICIAL NEURAL NETWORKS; 4. ESTIMATION OF THE CLASSIFICATION ERROR , 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 ISSUES3. MULTILAYER PERCEPTRON NETWORKS; 4. AN MLP IMPLEMENTATION OF TREE CLASSIFIERS; 5. TRAINING THE TREE MAPPED NETWORK; 6. PERFORMANCE EVALUATION; 7. CONCLUSIONS; REFERENCES; PART 2: APPLICATIONS; CHAPTER 6. Bayesian and neural network pattern recognition : atheoretical connection and empirical results with handwritten characters; Abstract; 1 Introduction; 2 Bayes Classifier; 3 Artificial Neural Networks and Back Propagation; 4 Relationship; 5 Experimental Results; 6 Discussion; 7 Conclusion; 8 Acknowledgements; References , CHAPTER 7. Shape and Texture Recognition by a Neural Network1. INTRODUCTION; 2. ZERNIKE MOMENT FEATURES FOR SHAPE RECOGNITION; 3. RANDOM FIELD FEATURES FOR TEXTURE RECOGNITION; 4. MULTI-LAYER PERCEPTRON CLASSIFIER; 5. CONVENTIONAL STATISTICAL CLASSIFIERS; 6. EXPERIMENTAL STUDY ON SHAPE CLASSIFICATION; 7. EXPERIMENTAL STUDY ON TEXTURE CLASSIFICATION; 8. DISCUSSIONS AND CONCLUSIONS; 9. REFERENCES; CHAPTER 8. Neural Networks for Textured Image Processing; Abstract; 1. INTRODUCTION; 2. DETECTION OF EDGES IN COMPUTER AND HUMAN VISION; 3. TEXTURE ANALYSIS USING MULTIPLE CHANNEL FILTERS , 4. NEURAL NETWORK APPROACHES , English

Additional Edition: ISBN 1-322-47236-X

Additional Edition: ISBN 0-444-88740-7

Language: English

UID:

Format: 1 Online-Ressource (XXI, 1095 p. 488 illus., 283 illus. in color)

Edition: 1st ed. 2020

ISBN: 9789811394065

Series Statement: Advances in Intelligent Systems and Computing 1006

Additional Edition: Erscheint auch als Druck-Ausgabe ISBN 978-981-139-405-8

Additional Edition: Erscheint auch als Druck-Ausgabe ISBN 978-981-139-407-2

Language: English

DOI: 10.1007/978-981-13-9406-5

URL: Volltext  (URL des Erstveröffentlichers)

UID:

Format: 1 Online-Ressource (XIII, 232 p. 110 illus)

ISBN: 9788132221968

Series Statement: Advances in intelligent systems and computing 332

Additional Edition: Erscheint auch als Druckausgabe ISBN 978-81-322-2195-1

Language: English

Keywords: Konferenzschrift

DOI: 10.1007/978-81-322-2196-8

URL: Volltext

URL: Inhaltsverzeichnis

URL: Abstract

UID:

Format: 1 Online-Ressource (XVIII, 878 p. 416 illus., 289 illus. in color)

Edition: 1st ed. 2021

ISBN: 9789811552434

Series Statement: Algorithms for Intelligent Systems

Additional Edition: Erscheint auch als Druck-Ausgabe ISBN 978-981-155-242-7

Additional Edition: Erscheint auch als Druck-Ausgabe ISBN 978-981-155-244-1

Language: English

DOI: 10.1007/978-981-15-5243-4

URL: Volltext  (URL des Erstveröffentlichers)

URL: Buchcover

UID:

Format: 1 Online-Ressource (XXX, 595 p. 354 illus., 222 illus. in color)

ISBN: 9789811326851

Series Statement: Lecture Notes in Electrical Engineering 524

Additional Edition: Erscheint auch als Druck-Ausgabe ISBN 978-981-132-684-4

Additional Edition: Erscheint auch als Druck-Ausgabe ISBN 978-981-132-686-8

Language: English

DOI: 10.1007/978-981-13-2685-1

URL: Volltext  (URL des Erstveröffentlichers)

UID:

Format: XVII, 333 S. , Ill., graph. Darst.

ISBN: 0792379799

Series Statement: The Kluwer international series in engineering and computer science SECS 582

Language: Undetermined

Subjects: Computer Science

Keywords: Multimedia ; Mehragentensystem ; Mensch-Maschine-Kommunikation

UID:

Format: 1 online resource (286 p.)

ISBN: 1-4832-9787-X

Series Statement: Machine Intelligence and Pattern Recognition ; Volume 11

Content: 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 curse of dimen

Note: Description based upon print version of record. , 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 , REFERENCESCHAPTER 2. LINKS BETWEEN ARTIFICIAL NEURAL NETWORKS (ANN) AND STATISTICAL PATTERN RECOGNITION; 1. Overview; 2. Neural Networks and Pattern Recognition - ̨Generalities; 3. Some Examples of ANN Paradigms; 4. Dynamic Systems and Control; 5. Conclusions; REFERENCES; CHAPTER 3. Small sample size problems in designing artificial neural networks; Abstract; 1. INTRODUCTION; 2. FINITE SAMPLE PROBLEMS IN STATISTICAL PATTERN RECOGNITION; 3. THE CLASSIFICATION ACCURACY AND TRAINING TIME OF ARTIFICIAL NEURAL NETWORKS; 4. ESTIMATION OF THE CLASSIFICATION ERROR , 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 ISSUES3. MULTILAYER PERCEPTRON NETWORKS; 4. AN MLP IMPLEMENTATION OF TREE CLASSIFIERS; 5. TRAINING THE TREE MAPPED NETWORK; 6. PERFORMANCE EVALUATION; 7. CONCLUSIONS; REFERENCES; PART 2: APPLICATIONS; CHAPTER 6. Bayesian and neural network pattern recognition : atheoretical connection and empirical results with handwritten characters; Abstract; 1 Introduction; 2 Bayes Classifier; 3 Artificial Neural Networks and Back Propagation; 4 Relationship; 5 Experimental Results; 6 Discussion; 7 Conclusion; 8 Acknowledgements; References , CHAPTER 7. Shape and Texture Recognition by a Neural Network1. INTRODUCTION; 2. ZERNIKE MOMENT FEATURES FOR SHAPE RECOGNITION; 3. RANDOM FIELD FEATURES FOR TEXTURE RECOGNITION; 4. MULTI-LAYER PERCEPTRON CLASSIFIER; 5. CONVENTIONAL STATISTICAL CLASSIFIERS; 6. EXPERIMENTAL STUDY ON SHAPE CLASSIFICATION; 7. EXPERIMENTAL STUDY ON TEXTURE CLASSIFICATION; 8. DISCUSSIONS AND CONCLUSIONS; 9. REFERENCES; CHAPTER 8. Neural Networks for Textured Image Processing; Abstract; 1. INTRODUCTION; 2. DETECTION OF EDGES IN COMPUTER AND HUMAN VISION; 3. TEXTURE ANALYSIS USING MULTIPLE CHANNEL FILTERS , 4. NEURAL NETWORK APPROACHES , English

Additional Edition: ISBN 1-322-47236-X

Additional Edition: ISBN 0-444-88740-7

Language: English

UID:

Format: 1 online resource (286 p.)

ISBN: 1-4832-9787-X

Series Statement: Machine Intelligence and Pattern Recognition ; Volume 11

Content: 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 curse of dimen

Note: Description based upon print version of record. , 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 , REFERENCESCHAPTER 2. LINKS BETWEEN ARTIFICIAL NEURAL NETWORKS (ANN) AND STATISTICAL PATTERN RECOGNITION; 1. Overview; 2. Neural Networks and Pattern Recognition - ̨Generalities; 3. Some Examples of ANN Paradigms; 4. Dynamic Systems and Control; 5. Conclusions; REFERENCES; CHAPTER 3. Small sample size problems in designing artificial neural networks; Abstract; 1. INTRODUCTION; 2. FINITE SAMPLE PROBLEMS IN STATISTICAL PATTERN RECOGNITION; 3. THE CLASSIFICATION ACCURACY AND TRAINING TIME OF ARTIFICIAL NEURAL NETWORKS; 4. ESTIMATION OF THE CLASSIFICATION ERROR , 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 ISSUES3. MULTILAYER PERCEPTRON NETWORKS; 4. AN MLP IMPLEMENTATION OF TREE CLASSIFIERS; 5. TRAINING THE TREE MAPPED NETWORK; 6. PERFORMANCE EVALUATION; 7. CONCLUSIONS; REFERENCES; PART 2: APPLICATIONS; CHAPTER 6. Bayesian and neural network pattern recognition : atheoretical connection and empirical results with handwritten characters; Abstract; 1 Introduction; 2 Bayes Classifier; 3 Artificial Neural Networks and Back Propagation; 4 Relationship; 5 Experimental Results; 6 Discussion; 7 Conclusion; 8 Acknowledgements; References , CHAPTER 7. Shape and Texture Recognition by a Neural Network1. INTRODUCTION; 2. ZERNIKE MOMENT FEATURES FOR SHAPE RECOGNITION; 3. RANDOM FIELD FEATURES FOR TEXTURE RECOGNITION; 4. MULTI-LAYER PERCEPTRON CLASSIFIER; 5. CONVENTIONAL STATISTICAL CLASSIFIERS; 6. EXPERIMENTAL STUDY ON SHAPE CLASSIFICATION; 7. EXPERIMENTAL STUDY ON TEXTURE CLASSIFICATION; 8. DISCUSSIONS AND CONCLUSIONS; 9. REFERENCES; CHAPTER 8. Neural Networks for Textured Image Processing; Abstract; 1. INTRODUCTION; 2. DETECTION OF EDGES IN COMPUTER AND HUMAN VISION; 3. TEXTURE ANALYSIS USING MULTIPLE CHANNEL FILTERS , 4. NEURAL NETWORK APPROACHES , English

Additional Edition: ISBN 1-322-47236-X

Additional Edition: ISBN 0-444-88740-7

Language: English

UID:

Format: 1 Online-Ressource (XX, 333 p)

ISBN: 9781475731965

Series Statement: The Springer International Series in Engineering and Computer Science 582

Content: Intelligent Multimedia Multi-Agent Systems focuses on building intelligent successful systems. The book adopts a human-centered approach and considers various pragmatic issues and problems in areas like intelligent systems, software engineering, multimedia databases, electronic commerce, data mining, enterprise modeling and human-computer interaction for developing a human-centered virtual machine. The authors describe an ontology of the human-centered virtual machine which includes four components: activity-centered analysis component, problem solving adapter component, transformation agent component, and multimedia based interpretation component. These four components capture the external and internal planes of the system development spectrum. They integrate the physical, social and organizational reality on the external plane with stakeholder goals, tasks and incentives, and organization culture on the internal plane. The human-centered virtual machine and its four components are used for developing intelligent multimedia multi-agent systems in areas like medical decision support and health informatics, medical image retrieval, e-commerce, face detection and annotation, internet games and sales recruitment. The applications in these areas help to expound various aspects of the human-centered virtual machine including, human-centered domain modeling, distributed intelligence and communication, perceptual and cognitive task modeling, component based software development, and multimedia based data modeling. Further, the applications described in the book employ various intelligent technologies like neural networks, fuzzy logic and knowledge based systems, software engineering artifacts like agents and objects, internet technologies like XML and multimedia artifacts like image, audio, video and text

Additional Edition: Erscheint auch als Druck-Ausgabe ISBN 9781441950086

Language: English

Subjects: Computer Science

Keywords: Multimedia ; Mehragentensystem ; Mensch-Maschine-Kommunikation

DOI: 10.1007/978-1-4757-3196-5

URL: Volltext  (URL des Erstveröffentlichers)