Artificial intelligence: A new synthesis (Record no. 4076)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 09909nam a22001937a 4500 |
| 020 ## - INTERNATIONAL STANDARD BOOK NUMBER | |
| International Standard Book Number | 9781558604674 |
| 040 ## - CATALOGING SOURCE | |
| Transcribing agency | CUS |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 006.3 |
| Item number | NIL/A |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | NIlsson, Nils J. |
| 245 ## - TITLE STATEMENT | |
| Title | Artificial intelligence: A new synthesis |
| Statement of responsibility, etc. | Nils J. Nilsson |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. (IMPRINT) | |
| Place of publication, distribution, etc. | Burlington, MA: |
| Name of publisher, distributor, etc. | Morgan Kaufmann Publishers, |
| -- | Elsevier, |
| Date of publication, distribution, etc. | 1998. |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | xxi, 513 p. |
| Other physical details | ill. |
| 504 ## - BIBLIOGRAPHY, ETC. NOTE | |
| Bibliography, etc | Includes bibliography and index |
| 505 ## - FORMATTED CONTENTS NOTE | |
| Formatted contents note | Introduction<br/>1.1 What Is AI?<br/>1.2 Approaches to Artificial lntelligence<br/>1.5 Brief History of AI<br/>1.4 Plan of the Book<br/>1.5 Additional Readings and Discussion<br/>I Reactive Machines<br/>Stimulus-Response Agents<br/>2.1 Perception and Action<br/>2.1.1 Perception<br/>2.1.2 Action<br/>2.1.3 Boolean Algebra<br/>2.1.4 Classes and Forms of Boolean Functions<br/>2.2 Representing and Implementing Action Functions 27<br/>2.2.1 Production Systems 27<br/>2.2.2 Networks 29<br/>2.2.5 The Subsumption Architecture 32<br/>2.5 Additional Readings and Discussion 33<br/>Neural Networks 57<br/>3.1 Introduction 37<br/>3.2 Training Single TLUs 38<br/>3.2.1 TLU Geometry 38<br/>3.2.2 Augmented Vectors 39<br/>3.2.3 Gradient Descent Methods 39<br/>3.2.4 The Widrow-Hoff Procedure 41<br/>3.2.5 The Generalized Delta Procedure 41<br/>3.2.6 The Error-Correction Procedure 43<br/>3.3 Neural Networks 44<br/>3.3.1 Motivation 44<br/>3.3.2 Notation 45<br/>3.3.3 The Backpropagation Method 46<br/>3.3.4 Computing Weight Changes in the Final Layer 48<br/>3.3.5 Computing Changes to the Weights in Intermediate Layers 3.4 Generalization, Accuracy, and Overfitting 51<br/>3.5 Additional Readings and Discussion 54<br/>Machine Evolution 59<br/>4.1 Evolutionary Computation 59<br/>4.2 Genetic Programming 60<br/>4.2.1 Program Representation in GP 60<br/>4.2.2 The GP Process<br/>4.2.3 Evolving a Wall-Following Robot 65<br/>4.5 Additional Readings and Discussion 69<br/>State Machines<br/>5.1 Representing the Environment by Feature Vectors 71<br/>5.2 Elman Networks<br/>5.5 Iconic Representations 74<br/>5.4 Blackboard Systems 77<br/>5.5 Additional Readings and Discussion<br/>6.1 Introduction<br/>6.2 Steering an Automobile<br/>6.5 Two Stages of Robot Vision<br/>6.4 Image Processing<br/>6.4.1 Averaging<br/>6.4.2 Edge Enhancement<br/>6.4.3 Combining Edge Enhancement with Averaging<br/>6.4.4 Region Finding<br/>6.4.5 Using Image Attributes Other Than Intensity 101<br/>6.5 Scene Analysis<br/>6.5.1 Interpreting Lines and Curves in the Image<br/>6.5.2 Model-Based Vision<br/>6.6 Stereo Vision and Depth Information 108<br/>6.7 Additional Readings and Discussion HO<br/>II Search in State Spaces 115<br/>7 Agents That Plan 117<br/>7.1 Memory Versus Computation 117<br/>1.1 State-Space Graphs 118<br/>7.3 Searching Explicit State Spaces 121<br/>7.4 Feature-Based State Spaces 122<br/>7.5 Graph Notation 124<br/>7.6 Additional Readings and Discussion 125<br/>8 Uninformed Search 129<br/>8.1 Formulating the State Space 129<br/>8.2 Components of Implicit State-Space Graphs 150<br/>8.3 Breadth-First Search 131<br/>8.4 Depth-First or Backtracking Search 133<br/>8.5 Iterative Deepening 135<br/>8.6 Additional Readings and Discussion 136<br/>9 Heuristic Search 139<br/>9.1 Using Evaluation Functions 139<br/>9.2 A General Graph-Searching Algorithm 141<br/>9.2.1 Algorithm A* 142<br/>9.2.2 Admissibility of A* 145<br/>9.2.3 The Consistency (or Monotone) Condition 150<br/>9.2.4 Iterative-Deepening A*<br/>9.2.5 Recursive Best-First Search 154<br/>9.3 Heuristic Functions and Search Efficiency 155<br/>9.4 Additional Readings and Discussion 160<br/>Planning, Acting, and Learning 165<br/>10.1 The Sense/Plan/Act Cycle 165<br/>10.2 Approximate Search 165<br/>10.2.1 Island-Driven Search 166<br/>10.2.2 Hierarchical Search 167<br/>10.2.3 Limited-Horizon Search 169<br/>10.2.4 Cycles <br/>10.2.5 Building Reactive Procedures 170<br/>10.3 Learning Heuristic Functions 172<br/>10.3.1 Explicit Graphs 172<br/>10.3.2 Implicit Graphs 175<br/>10.4 Rewards Instead of Goals 175<br/>10.5 Additional Readings and Discussion 177<br/>Alternative Search Formulations and<br/>Applications<br/>11.1 Assignment Problems 181<br/>11.2 Constructive Methods 185<br/>11.3 Heuristic Repair 187<br/>11.4 Function Optimization 189<br/>Adversarial Search 195<br/>12.1 Two-Agent Games 195<br/>12.2 The Minimax Procedure 197<br/>12.5 The Alpha-Beta Procedure 202<br/>12.4 The Search Efficiency of the Alpha-Beta Procedure 207<br/>12.5 Other Important Matters 208<br/>12.6 Games of Chance 208<br/>12.7 Learning Evaluation Functions 210<br/>12.8 Additional Readings and Discussion 212<br/>Ill Knowledge Representation and<br/>Reasoning 215<br/>The Propositional Calculus 217<br/>13.1 Using Constraints on Feature Values 217<br/>15.2 The Language 219<br/>15.5 Rules of Inference 220<br/>15.4 Definition of Proof 221<br/>15.5 Semantics 222<br/>15.5.1 Interpretations 222<br/>13.5.2 The Propositional Truth Table 225<br/>13.5.3 Satisfiability and Models 224<br/>13.5.4 Validity 224<br/>13.5.5 Equivalence 225<br/>13.5.6 Entailment 225<br/>15.6 Soundness and Completeness 226<br/>15.7 The PSAT Problem 227<br/>15.8 Other Important Topics 228<br/>13.8.1 Language Distinctions 228<br/>13.8.2 Metatheorems 22H<br/>13.8.3 Associative Laws 22*^<br/>13.8.4 Distributive Laws<br/>15.1 Motivation<br/>15.2 The Language and Its Syntax<br/>15.5 Semantics<br/>15.5.4 Knowledge<br/>15.4 Quantification<br/>15.5 Semantics of Quantifiers<br/>Resolution in the Propositional Calculus 231<br/>14.1 A New Rule of Inference: Resolution 231<br/>14.1.1 Clauses as wlfs<br/>14.1.2 Resolution on Clauses<br/>14.1.3 Soundness of Resolution<br/>14.2 Converting Arbitrary wffs to Conjunctions of Clauses<br/>14.5 Resolution Refutations<br/>14.4 Resolution Refutation Search Strategies<br/>14.4.1 Ordering Strategies<br/>14.4.2 Refinement Strategies<br/>14.5 Horn Clauses<br/>15.3 The Predicate Calculus 259<br/>15.3.1 Worlds<br/>15.3.2 Interpretations<br/>15.3.3 Models and Related Notions 243<br/>15.5.1 Universal Quantifiers 246<br/>15.5.2 Existential Quantifiers 247<br/>15.5.3 Useful Equivalences<br/>15.5.4 Rules of Inference<br/>15.6 Predicate Calculus as a Language for Representing<br/>Knowledge 248<br/>15.6.1 Conceptualizations<br/>15.6.2 Examples 248<br/>15.7 Additional Readings and Discussion 250<br/>Resolution in the Predicate Calculus 255<br/>16.1 Unification 255<br/>16.2 Predicate-Calculus Resolution 256<br/>16.5 Completeness and Soundness 257<br/>16.4 Converting Arbitrary wffs to Clause Form 257<br/>16.5 Using Resolution to Prove Theorems 260<br/>16.6 Answer Extraction 261<br/>16.7 The Equality Predicate 262<br/>16.8 Additional Readings and Discussion 265<br/>Knowledge-Based Systems 269<br/>Confronting the Real World 269<br/>Reasoning Using Horn Clauses 270<br/>Maintenance in Dynamic Knowledge Bases 275<br/>17.4 Rule-Based Expert Systems 280<br/>17.5 Rule Learning 286<br/>17.5.1 Learning Prepositional Calculus Rules 286<br/>17.5.2 Learning First-Order Logic Rules 291<br/>17.5.3 Explanation-Based Generalization 295<br/>17.6 Additional Readings and Discussion 297<br/>Representing Commonsense Knowledge <br/>18.1 The Commonsense World<br/>18.1.1 What Is Commonsense Knowledge?<br/>18.1.2 Difficulties in Representing Commonsense Knowledge<br/>18.1.3 The Importance of Commonsense Knowledge<br/>18.1.4 Research Areas<br/>18.2 Time<br/>18.3 Knowledge Representation by Networks<br/>18.5.1 Taxonomic Knowledge<br/>18.3.2 Semantic Networks<br/>18.3.3 Nonmonotonic Reasoning in Semantic Networks 309<br/>18.3.4 Frames<br/>18.4 Additional Readings and Discussion<br/>Reasoning with Uncertain Information 517<br/>19.1 Review of Probability Theory<br/>19.1.1 Fundamental Ideas<br/>19.1.2 Conditional Probabilities<br/>19.2 Probabilistic Inference<br/>19.2.1 A General Method<br/>19.2.2 Conditional Independence<br/>19.5 Bayes Networks<br/>19.4 Patterns of Inference in Bayes Networks<br/>19.5 Uncertain Evidence<br/>19.6 D-Separation<br/>19.7 Probabilistic Inference in Polytrees 532<br/>19.7.1 Evidence Above<br/>19.7.2 Evidence Below<br/>19.7.3 Evidence Above and Below 336<br/>19.7.4 A Numerical Example 336<br/>19.8 Additional Readings and Discussion 358<br/>Learning and Acting with Bayes Nets 345<br/>20.1 Learning Bayes Nets 343<br/>20.1.1 Known Network Structure 343<br/>20.1.2 Learning Network Structure 346<br/>20.2 Probabilistic Inference and Action 351<br/>20.2.1 The General Setting 351<br/>20.2.2 An Extended Example 552<br/>20.2.5 Generalizing the Example 556<br/>20.5 Additional Readings and Discussion 358<br/>IV Planning Methods Based on<br/>Logic 361<br/>The Situation Calculus 363<br/>21.1 Reasoning about States and Actions 563<br/>21.2 Some Difficulties 367<br/>21.2.1 Frame Axioms 367<br/>21.2.2 Qualifications 369<br/>21.2.3 Ramifications 369<br/>21.3 Generating Plans 369<br/>21.4 Additional Readings and Discussion 570<br/>Planning 575<br/>22.1 STRIPS Planning Systems 373<br/>22.1.1 Describing States and Goals 373<br/>22.1.2 Forward Search Methods 374<br/>22.1.3 Recursive STRIPS 376<br/>22.1.4 Plans with Run-Time Conditionals 379<br/>22.1.5 The Sussman Anomaly 380<br/>22.1.6 Backward Search Methods 381<br/>22.2 Plan Spaces and Partial-Order Planning 385<br/>22.3 Hierarchical Planning 393<br/>22.3.1 ABSTRIPS 393<br/>22.3.2 Combining Hierarchical and Partial-Order Planning 395<br/>22.4 Learning Plans 396<br/>22.5 Additional Readings and Discussion 398<br/>V Communication and Integration 405<br/>Multiple Agents 407<br/>25.1 Interacting Agents 407<br/>25.2 Models of Other Agents 408<br/>23.2.1 Varieties of Models 408<br/>23.2.2 Simulation Strategies 410<br/>23.2.3 Simulated Databases 410<br/>23.2.4 The Intentional Stance 411<br/>25.5 A Modal Logic of Knowledge 412<br/>23.3.1 Modal Operators 412<br/>23.3.2 Knowledge Axioms 413<br/>25.5.3 Reasoning about Other Agents'Knowledge 415<br/>25.5.4 Predicting Actions of Other Agents 417<br/>23.4 Additional Readings and Discussion 417<br/>Communication among Agents 421<br/>24.1 Speech Acts 421<br/>24.1.1 Planning Speech Acts 425<br/>24.1.2 Implementing Speech Acts 425<br/>24.2 Understanding Language Strings 425<br/>24.2.1 Phrase-Structure Grammars 425<br/>24.2.2 Semantic Analysis 428<br/>24.2.5 Expanding the Grammar 452<br/>24.3 Efficient Communication 435<br/>24.5.1 Use of Context 455<br/>24.5.2 Use of Knowledge to Resolve Ambiguities 456<br/>24.4 Natural Language Processing 437<br/>24.5 Additional Readings and Discussion 440<br/>Agent Architectures 443<br/>25.1 Three-Level Architectures 444<br/>25.2 Goal Arbitration 446<br/>25.3 The Triple-Tower Architecture 448<br/>25.4 Bootstrapping 449<br/>25.5 Additional Readings and Discussion 450<br/> |
| 650 ## - SUBJECT | |
| Keyword | Artificial intelligence |
| 650 ## - SUBJECT | |
| Keyword | Knowledge representation and reasoning |
| 650 ## - SUBJECT | |
| Keyword | Neural networks |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Koha item type | GN Books |
| Withdrawn status | Lost status | Damaged status | Not for loan | Home library | Current library | Shelving location | Date acquired | Full call number | Accession number | Date last seen | Koha item type |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Central Library, Sikkim University | Central Library, Sikkim University | General Book Section | 03/07/2016 | 006.3 NIL/A | P21209 | 03/07/2016 | General Books |