Normal view MARC view ISBD view

Parallel Processing for Artificial Intelligence 1.

By: Kanal, L.N.
Contributor(s): Kitano, H | Kumar, V | Suttner, C.B.
Material type: TextTextSeries: eBooks on Demand.Machine Intelligence and Pattern Recognition: Publisher: Burlington : Elsevier Science, 2014Description: 1 online resource (445 p.).ISBN: 9781483295749.Subject(s): Artificial intelligence | Parallel processing (Electronic computers)Genre/Form: Electronic books.Additional physical formats: Print version:: Parallel Processing for Artificial Intelligence 1DDC classification: 006.3 Online resources: Click here to view this ebook.
Contents:
Front Cover; Parallel Processing for Artificial Intelligence 1; Copyright Page; PREFACE; Table of Contents; EDITORS; AUTHORS; PART I: IMAGE PROCESSING; Chapter 1. A Perspective on Parallel Processing in Computer Vision and Image Understanding; 1. Introduction; 2. Parallelism in Vision Systems; 3. Representation Based Classification of Vision Computations; 4. Issues in Data and Computation Partitioning; 5. Architectural Requirements; 6. Future Directions; Acknowledgments; References; Chapter 2. On Supporting Rule-Based Image Interpretation Using a Distributed Memory Multicomputer
1. Introduction2. Software and Hardware Strategies for Supporting RBS; 3. AIMS: A Multi-Sensor Image Interpretation System; 4. Parallel Implementation; 5. Discussion; 6. Conclusion; References; Chapter 3. Parallel Affine Image Warping ; 1. Introduction; 2. Forward versus inverse algorithms in affine image warping; 3. Other important characteristics of affine image warping; 4. Machines; 5. Classification of implementations; 6. Systolic methods; 7. Data partitioned methods; 8. A scanline method; 9. A Sweep-Based Method; 10. Conclusions; References
Chapter 4. Image Processing On Reconfigurable Meshes With BusesAbstract; 1. Introduction; 2· Data Manipulation Operations; 3. Area And Perimeter Of Connected Components; 4. Shrinking And Expanding; 5. Clustering; 6. Template Matching; 7. Conclusions; 8. References; PART II: SEMANTIC NETWORKS; Chapter 5. Inheritance Operations in Massively Parallel Knowledge Representation; 1. Massively Parallel Knowledge Representation; 2. Schubert's Tree Encoding of IS-Á Hierarchies; 3. How to Achieve the Same Effect Without Trees; 4. Parallelizing the Update Algorithm; 5. Inheritance Terminology
6. Upward-Inductive Inheritance7. Downward Inheritance Algorithm; 8. Upward-Inductive Inheritance Algorith; 9. Experimental Results; 10. Conclusions; Acknowledgement ; References; Chapter 6. Providing Computationally Effective Knowledge Representation via Massive Parallelism; 1. Introduction; 2. Description of PARKA; 3. Performance; 4. Future & Related Work; 5. Conclusion; 6. Acknowledgments; References; PART III: PRODUCTION SYSTEMS III; Chapter 7. Speeding Up Production Systems: From Concurrent Matching to Parallel Rule Firing; 1. Introduction; 2. A Generic Production System Architecture
3. State-Saving Algorithms4. Parallel Execution of Rete; 5. Compile Time Optimization of Rete; 6. Parallel Rule Firing; 7. Discussion; References; Chapter 8. Guaranteeing Serializability in Parallel Production Systems; 1. Execution Models for Production Systems; 2. The Serialization Problem; 3. Ishida and Stolfo's Work; 4. Definitions and Tests; 5. Solution to the Serialization Problem; 6. Algorithms to Guarantee Serializaibilty; 7. Performance Analysis; 8. Related Work; 9. Conclusions; 10. Acknowledgments; References; PART IV: MECHANIZATION OF LOGIC IV
Chapter 9. Parallel Automated Theorem Proving
Summary: Parallel processing for AI problems is of great current interest because of its potential for alleviating the computational demands of AI procedures. The articles in this book consider parallel processing for problems in several areas of artificial intelligence: image processing, knowledge representation in semantic networks, production rules, mechanization of logic, constraint satisfaction, parsing of natural language, data filtering and data mining. The publication is divided into six sections. The first addresses parallel computing for processing and understanding images. The second discus
Tags from this library: No tags from this library for this title. Log in to add tags.
Item type Current location Call number URL Status Date due Barcode
Electronic Book UT Tyler Online
Online
QA76.58 .P37775 2014 (Browse shelf) http://uttyler.eblib.com/patron/FullRecord.aspx?p=1877103 Available EBL1877103

Front Cover; Parallel Processing for Artificial Intelligence 1; Copyright Page; PREFACE; Table of Contents; EDITORS; AUTHORS; PART I: IMAGE PROCESSING; Chapter 1. A Perspective on Parallel Processing in Computer Vision and Image Understanding; 1. Introduction; 2. Parallelism in Vision Systems; 3. Representation Based Classification of Vision Computations; 4. Issues in Data and Computation Partitioning; 5. Architectural Requirements; 6. Future Directions; Acknowledgments; References; Chapter 2. On Supporting Rule-Based Image Interpretation Using a Distributed Memory Multicomputer

1. Introduction2. Software and Hardware Strategies for Supporting RBS; 3. AIMS: A Multi-Sensor Image Interpretation System; 4. Parallel Implementation; 5. Discussion; 6. Conclusion; References; Chapter 3. Parallel Affine Image Warping ; 1. Introduction; 2. Forward versus inverse algorithms in affine image warping; 3. Other important characteristics of affine image warping; 4. Machines; 5. Classification of implementations; 6. Systolic methods; 7. Data partitioned methods; 8. A scanline method; 9. A Sweep-Based Method; 10. Conclusions; References

Chapter 4. Image Processing On Reconfigurable Meshes With BusesAbstract; 1. Introduction; 2· Data Manipulation Operations; 3. Area And Perimeter Of Connected Components; 4. Shrinking And Expanding; 5. Clustering; 6. Template Matching; 7. Conclusions; 8. References; PART II: SEMANTIC NETWORKS; Chapter 5. Inheritance Operations in Massively Parallel Knowledge Representation; 1. Massively Parallel Knowledge Representation; 2. Schubert's Tree Encoding of IS-Á Hierarchies; 3. How to Achieve the Same Effect Without Trees; 4. Parallelizing the Update Algorithm; 5. Inheritance Terminology

6. Upward-Inductive Inheritance7. Downward Inheritance Algorithm; 8. Upward-Inductive Inheritance Algorith; 9. Experimental Results; 10. Conclusions; Acknowledgement ; References; Chapter 6. Providing Computationally Effective Knowledge Representation via Massive Parallelism; 1. Introduction; 2. Description of PARKA; 3. Performance; 4. Future & Related Work; 5. Conclusion; 6. Acknowledgments; References; PART III: PRODUCTION SYSTEMS III; Chapter 7. Speeding Up Production Systems: From Concurrent Matching to Parallel Rule Firing; 1. Introduction; 2. A Generic Production System Architecture

3. State-Saving Algorithms4. Parallel Execution of Rete; 5. Compile Time Optimization of Rete; 6. Parallel Rule Firing; 7. Discussion; References; Chapter 8. Guaranteeing Serializability in Parallel Production Systems; 1. Execution Models for Production Systems; 2. The Serialization Problem; 3. Ishida and Stolfo's Work; 4. Definitions and Tests; 5. Solution to the Serialization Problem; 6. Algorithms to Guarantee Serializaibilty; 7. Performance Analysis; 8. Related Work; 9. Conclusions; 10. Acknowledgments; References; PART IV: MECHANIZATION OF LOGIC IV

Chapter 9. Parallel Automated Theorem Proving

Parallel processing for AI problems is of great current interest because of its potential for alleviating the computational demands of AI procedures. The articles in this book consider parallel processing for problems in several areas of artificial intelligence: image processing, knowledge representation in semantic networks, production rules, mechanization of logic, constraint satisfaction, parsing of natural language, data filtering and data mining. The publication is divided into six sections. The first addresses parallel computing for processing and understanding images. The second discus

Description based upon print version of record.

There are no comments for this item.

Log in to your account to post a comment.