The Pattern Recognition Basis of Artificial Intelligence (häftad)
Fler böcker inom
Häftad (Paperback)
Antal sidor
IEEE Computer Society Press,U.S.
266 x 190 x 25 mm
816 g
Antal komponenter

The Pattern Recognition Basis of Artificial Intelligence

Häftad, Engelska, 1998-02-01
967 kr
Skickas inom 5-8 vardagar.
Fri frakt inom Sverige för privatpersoner.
This book takes the viewpoint that plain symbol processing techniques have little hope of reproducing the depth and breadth of capabilities found in human beings. The book introduces new foundational principles to AI: connectionist/neural networking methods, case based and memory based methods and picture processing. The book looks at methods of AI as different ways of doing pattern recognition. One way to do pattern recognition is to compare a problem to stored cases. At the other end of the spectrum, Classical Symbol Processing AI compresses cases down to a small set of rules and then works only with this condensed knowledge. In between these two extremes are neural networks, especially backprop type networks. As much as possible the book compares these three basic methods using actual AI programs. The structure of the book starts at the bottom of human abilities with vision and other simple pattern recognition abilities and moves on to the higher levels of problem solving and game playing and finally to the level of natural language and understanding of the world. At the higher levels more complex computer architectures are needed that include methods for structuring thoughts. The book is organized in a manner in which the reader will get an intuitive feeling for the principles of AI. Throughout the book applications of basic principles are demonstrated by examining some classic AI programs in detail. The book can serve as a text for juniors, seniors and first year graduate students in Computer Science or Psychology and includes sample problems and data for exercises and a list of frequently asked questions.
Visa hela texten


Har du läst boken? Sätt ditt betyg »

Bloggat om The Pattern Recognition Basis of Artifici...


Preface. 1 Artificial Intelligence. 1.1 Artificial Intelligence and Intelligence 1.1.1 Intelligence. 1.1.2 Thinking. 1.1.3 The Turing Test for Thinking. 1.1.4 The Chinese Room Argument. 1.1.5 Consciousness and Quantum Mechanics. 1.1.6 Dualism. 1.2 Association. 1.3 Neural Networking. 1.3.1 Artificial Neural Networks. 1.3.2 Biological Neural Networks. 1.4 Symbol Processing. 1.5 Heuristic Search. 1.6 The Problems with AI. 1.7 The New Proposals. 1.7.1 Real Numbers. 1.7.2 Picture Processing. 1.7.3 Memories. 1.7.4 Quantum Mechanics. 1.8 The Organization of the Book. 1.9 Exercises. 2 Pattern Recognition I. 2.1 A Simple Pattern Recognition Algorithm. 2.2 A Short Description of the Neocognitron. 2.2.1 Detecting Short Lines. 2.2.2 A Typical Neocognitron. 2.2.3 Training the Neocognitron. 2.2.4 Some Results. 2.3 Recognizing Words. 2.4 Expanding the Pattern Recognition Hierarchy. 2.4.1 Hearing. 2.4.2 Higher Levels. 2.4.3 The Hierarchy. 2.4.4 On the Hierarchy. 2.5 Additional Perspective. 2.5.1 Other Systems. 2.5.2 Realism. 2.5.3 Bigger Problems. 2.6 Exercises. 3 Pattern Recognition II. 3.1 Mathematics, Pattern Recognition, and the Linear Pattern Classifier. 3.1.1 The Linear Pattern Classifier. 3.1.2 ADALINEs and MADELINEs. 3.1.3 Perceptrons. 3.2 Separating Nonlinearly Separable Classes. 3.2.1 The Nearest Neighbor Algorithm. 3.2.2 Learning Vector Quantization Methods. 3.3 Hopfield Networks. 3.3.1 The Hopfield Network. 3.3.2 Storing Patterns. 3.3.3 The Boltzman Machine. 3.3.4 Pattern Recognition. 3.3.5 Harmony. 3.3.6 Comparison with Human Thinking. 3.4 Back--Propagation. 3.4.1 History. 3.4.2 The Network. 3.4.3 Computing the Weights. 3.4.4 Speeding Up Back--Propagation. 3.4.5 Dealing with Local Minima. 3.4.6 Using Back--Propagation to Train Hopfield/Boltzman Networks. 3.5 Pattern Recognition and Curve Fitting. 3.5.1 Pattern Recognition as Curve Fitting. 3.5.2 Approximating Real--Valued Functions. 3.5.3 Overfitting. 3.6 Associative Memory and Generalization. 3.6.1 Associative Memory. 3.6.2 Local and Distributed Representations. 3.6.3 Reasoning within a Network. 3.7 Applications of Back--Propagation. 3.7.1 Interpreting Sonar Returns. 3.7.2 Reading Text. 3.7.3 Speech Recognition. 3.7.4 Detecting Bombs. 3.7.5 Economic Analysis. 3.7.6 Learning to Drive. 3.7.7 DNA Analysis. 3.8 Additional Perspective. 3.9 Exercises. 4 Rule--Based Methods. 4.1 Introduction. 4.2 Some Elementary Prolog. 4.2.1 Stating Facts. 4.2.2 Syntax. 4.2.3 Asking Questions. 4.2.4 Rules. 4.2.5 Recursion. 4.2.6 List Processing. 4.2.7 Other Predicates. 4.3 Rules and Basic Rule Interpretation Methods. 4.3.1 A Small Rule--Based System. 4.3.2 Forward Chaining. 4.3.3 Backward Chaining. 4.4 Conflict Resolution. 4.5 More Sophisticated Rule Interpretation. 4.5.1 Dealing with Incomplete Data by Asking Questions. 4.5.2 Other Activation Functions. 4.5.3 Uncertain Input. 4.5.4 Extra Facilities for Rule Interpreters. 4.6 The Famous Expert Systems. 4.6.1 DENDRAL. 4.6.2 MYCIN. 4.6.3 PROSPECTOR. 4.6.4 ACE. 4.6.5 XCON. 4.7 Learning Rules in SOAR. 4.7.1 A Searching Example. 4.7.2 The Power Law of Practice. 4.8 Rules versus Networks. 4.9 Exercises. 5 Logic. 5.1 Standard Form and Clausal Form. 5.2 Basic Inference Rules. 5.2.1 Inference Rules. 5.2.2 Clauses with Variables. 5.3 Controlling Search. 5.3.1 The Problem with Blind Searching. 5.3.2 Proof by Contradiction. 5.3.3 The Set--of--Support Strategy. 5.3.4 Weighting. 5.3.5 Prolog's Strategy. 5.4 An Example Using Otter. 5.4.1 The Problem. 5.5 The Usefulness of Predicate Calculus. 5.6 Other Reasoning Methods. 5.7 Exercises. 6 Complex Architectures. 6.1 The Basic Human Architecture. 6.2 Flow of Control. 6.3 The Virtual Symbol Processing Machine Proposal. 6.4 Mental Representation and Computer Representation. 6.4.1 A Problem with Symbolic Representation. 6.4.2 Symbol Grounding as a Solution. 6.4.3 Structure and Operations on Structures. 6.5 Storing Sequential Events. 6.5.1 The Symbolic Solution. 6.5.2 Neural Solutions. 6.6 Structuring Individual Thoughts.