du Boulay / Sgurev Artificial Intelligence V

Methodology, Systems, Applications
1. Auflage 2014
ISBN: 978-1-4832-9779-8
Verlag: Elsevier Science & Techn.
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 290 Seiten, Web PDF

Recent results and ongoing research in Artificial Intelligence are described in this book, with emphasis on fundamental questions in several key areas: machine learning, neural networks, automated reasoning, natural language processing, and logic methods in AI. There are also more applied papers in the fields of vision, architectures for KBS, expert systems and intelligent tutoring systems. One of the changes since AIMSA'90 has been the increased numbers of papers submitted in the fields of machine learning, neural networks and hybrid systems.One of the special features of the AIMSA series of conferences is their coverage of work across both Eastern and Western Europe and the former Soviet Union as well as papers from North America. AIMSA'92 is no exception and this volume provides a unique multi-cultural view of AI.

Autoren/Hrsg.

du Boulay, B.

Sgurev, V.

Inhaltsverzeichnis

1;Front Cover;1
2;Artificial Intelligence V: Methodology, Systems, Applications;4
3;Copyright Page;5
4;Table of Contents;12
5;FOREWORD;6
6;ACKNOWLEDGEMENTS;8
7;CHAIRMAN OF THE CONFERENCE;10
8;PART I:
AUTOMATED REASONING;16
8.1;CHAPTER 1.
SIMILARITY IN ANALOGICAL REASONING;18
8.1.1;1. INTRODUCTION;18
8.1.2;2. BACKGROUND;19
8.1.3;3. SIMILARITY IN CONTEXT;20
8.1.4;4. TYPES OF SIMILARITY IN ANALOGICAL REASONING;21
8.1.5;5. COMPUTATION OF SIMILARITY IN THE DUAL ARCHITECTURE;22
8.1.6;6. EXPLANATION OF EXPERIMENTAL FACTS;24
8.1.7;7. CONCLUSIONS;26
8.1.8;ACKNOWLEDGEMENTS;26
8.1.9;REFERENCES;26
8.2;Chapter 2.
Using Bayesian Networks for Technical Diagnosis;28
8.2.1;1. INTRODUCTION;28
8.2.2;2. FORMULATION OF
THE DIAGNOSTIC PROBLEM;29
8.2.3;3. PROBABILISTIC INFERENCE IN DB - NET AS DIRECTED TREE;30
8.2.4;4. PROBABILISTIC INFERENCE IN SINGLY CONNECTED DB-NETS;35
8.2.5;5. CONCLUSION;38
8.2.6;6. REFERENCES;38
8.3;Chapter 3.
Applications of Assertions as Elementary Tactics in Proof Planning;40
8.3.1;1.
Introduction;40
8.3.2;2.
General Framework of a Computational Model;41
8.3.3;3.
Applications of Rules of Inference;42
8.3.4;4.
Deriving Associated Rules;43
8.3.5;5.
Applications of Assertions;44
8.3.6;6.
Conclusion and Future Work;48
8.3.7;References;49
8.4;Chapter 4.
Plans as Planning Objects;50
8.4.1;0. INTRODUCTION;50
8.4.2;1. THE PLANNING MODEL;51
8.4.3;2. FROM NONLINEAR/PARALLEL PLAN DESCRIPTION TO PLAN
OBJECT DESCRIPTION;53
8.4.4;3. CORRECTNESS OF PLAN OBJ DESCRIPTIONS;57
8.4.5;4. CONCLUSIONS;58
8.4.6;5. REFERENCES;59
9;PART
II: LOGIC METHODS IN AI;60
9.1;Chapter 5.
Logical Approaches to Structured Knowledge Bases;62
9.1.1;1 Introduction and motivation;62
9.1.2;2 Basics of logic programming;65
9.1.3;3 Modular knowledge bases;65
9.1.4;4 An approach to structured knowledge bases;69
9.1.5;5 Further research;70
9.1.6;References;70
9.2;CHAPTER
6. LOGIC PROGRAMMING WITH WORLDS;72
9.2.1;1.
Introduction;72
9.2.2;2.
W-Prolog and its underlying features;73
9.2.3;3.
Further directions of development;79
9.2.4;4.
Related works;80
9.2.5;5.
Acknowledgments;80
9.2.6;REFERENCES;81
9.3;Chapter 7.
Inconsistent information processing in knowledge based systems;82
9.3.1;1. INTRODUCTION;82
9.3.2;2. DETECTION OF CONTRADICTIONS;83
9.3.3;3. BASIC FEATURES OF THE REASONING ON THE BASIS OF AN INCONSISTENT KNOWLEDGE;85
9.3.4;4. GRAPHICAL INTERPRETATION OF THE INFERENCE PROCESS;85
9.3.5;5. WAYS FOR SETTING UP THE HEURISTIC ESTIMATIONS;88
9.3.6;6. EXPERIMENTS, RESULTS AND PERSPECTIVES;89
9.3.7;7. CONCLUSIONS;90
9.3.8;7. REFERENCES;90
9.4;Chapter 8.
Non-Monotonic Logics: A Valuations-Based Approach;92
9.4.1;1. Introduction;92
9.4.2;2. Inference Relations on the Lattice of Valuations;93
9.4.3;3. An Application of the Framework;94
9.4.4;4. Linking Logics to Inference Relations;95
9.4.5;5· Monotonicity;97
9.4.6;6. Conclusion;99
9.4.7;7. Acknowledgements;99
9.4.8;8. References;99
10;PART III:
MACHINE LEARNING;100
10.1;Chapter 9.
Combining decisions of multiple rules;102
10.1.1;1.
INTRODUCTION;102
10.1.2;2.
STOCHASTIC LEARNING ALGORITHMS;103
10.1.3;3.
COMBINATION RULES;105
10.1.4;4.
EXPERIMENTS;106
10.1.5;5.
DISCUSSION;110
10.1.6;Acknowledgements;111
10.1.7;References;111
10.2;Chapter 10.
Space Fragmenting - A Method For Disjunctive Concept Acquisition;112
10.2.1;I. Introduction;112
10.2.2;II. Space Fragmenting Description;113
10.2.3;III.
Example;115
10.2.4;IV. Conclusion;119
10.2.5;REFERENCES;119
10.3;Chapter 11.
Some Experiments with a Stochastic Production System for Supervised Inductive Learning;120
10.3.1;1. INTRODUCTION;120
10.3.2;2. SUPERVISED CONCEPT LEARNING AND GENETIC ALGORITHMS;121
10.3.3;3. SYSTEM DESCRIPTION;122
10.3.4;4. MORE EXPERIMENTS;125
10.3.5;5. SUMMARY;128
10.3.6;References;129
10.4;Chapter 12.
The Range Scale as Result of Inductive Learning;130
10.4.1;1. INTRODUCTION;130
10.4.2;2 . SCALE INDUCTION: THE BASEMENT;131
10.4.3;3 . FORMAL DESCRIPTION OF SCALE INDUCTION;133
10.4.4;4 . IMPLEMENTATION;136
10.4.5;5. CONCLUSION AND FURTHER DEVELOPMENTS;137
10.4.6;6. REFERENCES;138
10.4.7;APPENDIX;138
10.5;Chapter 13.
Analysis of Classification With Two Classifiers;140
10.5.1;1. Introduction;140
10.5.2;2. Classification with independent classifiers;141
10.5.3;3. Special cases;142
10.5.4;4. The influence of dependance on classification accuracy;143
10.5.5;5. Conclusions;144
10.5.6;References;145
11;PART IV:
NEURAL NETWORKS;146
11.1;Chapter 14. Applying Fast Optimization Methods for Supervised Learning in Feedforward Neural
Networks;148
11.1.1;1. INTRODUCTION;148
11.1.2;2. BASICS;149
11.1.3;3. THE NEW APPROACH;150
11.1.4;4. IMPLEMENTATION;153
11.1.5;5. CONCLUSIONS;154
11.1.6;ACKNOWLEDGMENTS;154
11.1.7;REFERENCES;154
11.2;Chapter 15.
Prognostic Expert Systems on a Hybrid Connectionist Environment;156
11.2.1;1. INTRODUCTION;156
11.2.2;2. A HYBRID CONNECTIONIST RULE-BASED ENVIRONMENT AND ITS APPLICABILITY TO TEMPORAL PROGNOSIS;157
11.2.3;3. A CONNECTIONIST PROGNOSTIC MODEL;158
11.2.4;4. THE HIGHER, SYMBOLIC LEVEL OF THE HYBRID PROGNOSTIC SYSTEM;161
11.2.5;5. AN EXPERT SYSTEM FOR AN AGRICULTURAL INSECT PROGNOSIS;161
11.2.6;6. CONCLUSIONS;162
11.2.7;7. ACKNOWLEDGEMENTS;163
11.2.8;8. REFERENCES;163
12;PART V:
NATURAL LANGUAGE PROCESSING;164
12.1;Chapter 16.
Grammar Representation and Parsing in a Data-Driven Logic Programming Environment;166
12.1.1;1. INTRODUCTION;166
12.1.2;2. OVERVIEW OF THE DD-RULE FORMALISM;167
12.1.3;3. GRAMMAR REPRESENTATION BY MEANS OF DD-RULES;168
12.1.4;4. THE PARSING METHOD;170
12.1.5;5. RELATED WORK;173
12.1.6;6. CONCLUSION;173
12.1.7;7. REFERENCES;174
12.2;Chapter 17.
Extending Definite Clause Grammar to handle flexible word order;176
12.2.1;1. INTRODUCTION;176
12.2.2;2. WORD ORDER AND LOGIC GRAMMARS;177
12.2.3;3. FLEXIBLE WORD ORDER GRAMMAR;177
12.2.4;4. AN EXAMPLE FROM BULGARIAN;179
12.2.5;5. TWO IMPLEMENTATIONS;180
12.2.6;6. CONCLUSION;183
12.2.7;7. REFERENCES;183
12.2.8;APPENDIX;184
12.3;Chapter 18.
MODALYS: A System for the Semantic-Pragmatic Analysis of Modal Verbs;186
12.3.1;1.
The importance of modal verbs;186
12.3.2;2.
Some aspects of the semantics of modal verbs;187
12.3.3;3.
The disambiguation component DIA;189
12.3.4;4.
An operational semantics for the readings of the modal verbs;190
12.3.5;5.
Modal verbs in compound sentences;192
12.3.6;6.
Implementation;194
12.3.7;7.
Comparision with related work;194
12.3.8;8.
Conclusion and future work;194
12.3.9;References;195
12.4;Chapter 19.
A System For Text Temporal Information Retrieval;196
12.4.1;1.
Introduction;196
12.4.2;2.
Temporal ontology;197
12.4.3;3.
The interpretation context;199
12.4.4;4.
A Theory of action;200
12.4.5;5.
Illustration;202
12.4.6;6.
Conclusion and related work;204
12.4.7;References;204
13;PART VI: KNOWLEDGE BASED SYSTEMS
– METHODS AND ARCHITECTURES;206
13.1;CHAPTER
20. .... THEORY AS A TOOL FOR INTEGRATION AND CONTROL;208
13.1.1;1. Introduction;208
13.1.2;2. An example SGES architecture;209
13.1.3;3. REFLOG;210
13.1.4;4. Meta theory;212
13.1.5;5· Summary;216
13.1.6;References;216
13.2;Chapter 21.
Systems-Based Knowledge Representation: Relations and Methods;218
13.2.1;1. INTRODUCTION;218
13.2.2;2. THE GENERAL MODEL OF SYSTEMS;219
13.2.3;3. RELATIONS AND METHODS;220
13.2.4;4. PROBLEM SOLVING WITH SYSTEMS;222
13.2.5;5. NEURAL NETWORKS AS SYSTEMS;225
13.2.6;6. CONCLUSIONS;227
13.2.7;REFERENCES;227
13.3;Chapter 22.
COPE - a Flexible Constraint-Based Programming System for Knowledge Processing;228
13.3.1;1. INTRODUCTION;228
13.3.2;2. CONSTRAINT REPRESENTATION IN COPE;229
13.3.3;3. THE INTEGRATION OF CONSTRAINTS AND OBJECTS;235
13.3.4;4. CONCLUSIONS;235
13.3.5;REFERENCES;236
13.4;Chapter 23.
A two-headed architecture for intelligent multimedia man-machine interaction;238
13.4.1;1.
Introduction;238
13.4.2;2.
Architecture;239
13.4.3;3.
Interactional Decision Center;242
13.4.4;4.
Reflectional Decision Center;244
13.4.5;5.
An application: Dynamic lexical databases;245
13.4.6;6.
Conclusions and future work;246
13.4.7;References;247
14;PART
VII: APPLICATIONS OF KNOWLEDGE BASED SYSTEMS;248
14.1;Chapter 24.
Discovery Environments for the Domain of Computer Programming: A Methodology;250
14.1.1;1. INTRODUCTION;250
14.1.2;2. A SYNTHESIS-BASED APPROACH;251
14.1.3;3. A VISIBLE PROGRAMMING DOMAIN;251
14.1.4;4. AUTOMATIC TUTORING;252
14.1.5;5. IMMEDIATE FEEDBACK;253
14.1.6;6. LEARNING FROM EXAMPLES;254
14.1.7;7. THE IMPLEMENTATION;254
14.1.8;8. ACKNOWLEDGEMENT;258
14.1.9;REFERENCES;258
14.2;CHAPTER 25.
AN EXPERT SYSTEM FOR RESOURCE ESTIMATION AND COST ANALYSIS;262
14.2.1;1. INTRODUCTION;262
14.2.2;2. SOFTWARE COST MODEL;263
14.2.3;3. KNOWLEDGE BASE;265
14.2.4;4. SYSTEM ARCHITECTURE;266
14.2.5;5. CONCLUSION;267
14.2.6;6. REFERENCES;268
14.3;Chapter 26.
A Knowledge Based System for Automatic 3D Scene Generation;270
14.3.1;1.
Introduction;270
14.3.2;2.
NALIG architecture;271
14.3.3;3.
NALIG knowledge base;273
14.3.4;4.
The symbolic module;273
14.3.5;5.
The positioning module;277
14.3.6;6.
Conclusions;279
14.3.7;References;279
14.4;Chapter 27.
Towards an Application of Intelligent Image Analysis System to Robotic Fettling of Castings;280
14.4.1;1.
INTRODUCTION;280
14.4.2;2. STRUCTURING AND REPRESENTATION OF CASTING KNOWLEDGE IN ISIA;281
14.4.3;3. STAGES OF INFORMATION EXTRACTION FROM IMAGES;283
14.4.4;4. IMPLEMENTATION;286
14.4.5;5.
CONCLUSION;287
14.4.6;6.
REFERENCES;287
15;AUTHOR INDEX;290