Neural Networks and Intellect: Using Model-Based Concepts / Edition 1

by Leonid I. Perlovsky

Overview

Neural Networks and Intellect: Using Model-Based Concepts describes a new mathematical concept of modeling field theory and its applications to a variety of problems. Examining the relationships among mathematics, computations in neural networks, signs and symbols in semiotics, and ideas of mind in psychology and philosophy, this unique text discusses deep philosophical questions in detail and relates them to mathematics and the engineering of intelligence. Ideal for courses in neural networks, modern pattern recognition, and mathematical concepts of intelligence, it will also be of interest to anyone working in a variety of fields including neural networks, AI, cognitive science, fuzzy systems, pattern recognition and machine/computer vision, data mining, robotics, target tracking, and financial forecasting.
Neural Networks and Intellect describes model-based neural networks that utilize the intriguing concept of an internal "world" model, an idea that originated in artificial intelligence and cognitive psychology but whose roots date back to Plato and Aristotle. Combining the a priori knowledge with adaptive learning, the new mathematical concept addresses the most perplexing problems in the field of neural networks: fast learning and robust generalization. The author provides an overview of computational intelligence and neural networks, relating hundreds of seemingly disparate techniques to several fundamental mathematical concepts, which are in turn linked to concepts of mind in philosophy, psychology, and linguistics. Topics covered include the hierarchical and heterarchical organization of intelligent systems, statistical learning theory, genetic algorithms, complex adaptive systems, mathematical semiotics, the dynamic nature of symbols, Godel theorems and intelligence, emotions and thinking, the mathematics of emotional intellect, consciousness, and more. Perlovsky's remarkable conclusion is that the work of ancient philosophers came closer to the computational concepts emerging today than that of pattern recognition and AI experts of just a few years ago.
The following website contains information about Dr. Perlovsky's current research related to the theory developed in the book and about available funding opportunities under a Research Associateship Program: to find it search for Perlovsky on http://www4/nationalacademies.org/pga/rap.nsf. Other sources of funding might be available for US-based and international researchers.

Product Details

ISBN-13:	9780195111620
Publisher:	Oxford University Press
Publication date:	10/19/2000
Edition description:	New Edition
Pages:	496
Product dimensions:	9.50(w) x 7.50(h) x 1.11(d)

About the Author

Ascent Capital Management

Table of Contents

Chapters 1-7, 9, and 10 end with Notes, Bibliographical Notes, and ProblemsChapter 8 ends with Bibliographical Notes and ProblemsChapters 11 and 12 end with Notes and Bibliographical NotesPrefacePART ONE: OVERVIEW: 2300 YEARS OF PHILOSOPHY, 100 YEARS OF MATHEMATICAL LOGIC, AND 50 YEARS OF COMPUTATIONAL INTELLIGENCE1. Introduction: Concepts of Intelligence1.1. Concepts of Intelligence in Mathematics, Psychology, and Philosophy1.2. Probability, Hypothesis Choice, Pattern Recognition, and Complexity1.3. Prediction, Tracking, and Dynamic Models1.4. Preview: Intelligence, Internal Model, Symbol, Emotions, and Consciousness2. Mathematical Concepts of Mind2.1. Complexity, Aristotle, and Fuzzy Logic2.2. Nearest Neighbors and Degenerate Geometries2.3. Gradient Learning, Back Propagation, and Feedforward Neural Networks2.4. Rule-Based Artificial Intelligence2.5. Concept of Internal Model2.6. Abductive Reasoning2.7. Statistical Learning Theory and Support Vector Machines2.8. AI Debates Past and Future2.9. Society of Mind2.10. Sensor Fusion and JDL Model2.11. Hierarchical Organization2.12. Semiotics2.13. Evolutionary Computation, Genetic Algorithms, and CAS2.14. Neural Field Theories2.15. Intelligence, Learning, and Computability3. Mathematical versus Metaphysical Concepts of Mind3.1. Prolegomenon: Plato, Antisthenes, and Artifical Intelligence3.2. Learning from Aristotle to Maimonides3.3. Heresy of Occam and Scientific Method3.4. Mathematics vs. Physics3.5. Kant: Pure Spirit and Psychology3.6. Freud vs. Jung: Psychology of Philosophy3.7. Wither We Go From Here?PART II: MODELING FIELD THEORY: NEW MATHEMATICAL THEORY OF INTELLIGENCE WITH EXAMPLES OF ENGINEERING APPLICATIONS4. Modeling Field Theory4.1. Internal Models, Uncertainties, and Similarities4.2. Modeling Field Theory Dynamics4.3. Bayesian MFT4.4. Shannon-Einsteinian MFT4.5. Modeling Field Theory Neural Architecture4.6. Convergence4.7. Learning of Structures, AIC, and SLT4.8. Instinct of World Modeling: Knowledge Instinct5. MLANS: Maximum Likelihood Adaptive Neural System for Grouping and Recognition5.1. Grouping, Classification, and Models5.2. Gaussian Mixture Model: Unsupervised Learning or Grouping5.3. Combined Supervised and Unsupervised Learning5.4. Structure Estimation5.5. Wishart and Rician Mixture Models for Radar Image Classification5.6. Convergence5.7. MLANS, Physics, Biology, and Other Neural Networks6. Einsteinian Neural Network6.1. Images, Signals, and Spectra6.2. Spectral Models6.3. Neural Dynamics of ENN6.4. Applications to Acoustic Transient Signals and Speech Recognition6.5. Applications to Electromagnetic Wave Propagation in the Ionosphere6.6. Summary6.7. Appendix7. Prediction, Tracking, and Dynamic Models7.1. Prediction, Association, and Nonlinear Regression7.2. Association and Tracking Using Bayesian MFT7.3. Association and Tracking Using Shannon-Einsteinian MFT (SE-CAT)7.4. Sensor Fusion MFT7.5. Attention8. Quantum Modeling Field Theory (QMFT)8.1. Quantum Computing and Quantum Physics Notations8.2. Gibbs Quantum Modeling Field System8.3. Hamiltonian Quantum Modeling Field System9. Fundamental Limitations on Learning9.1. The Cramer-Rao Bound on Speed of Learning9.2. Overlap Between Classes9.3. CRB for MLANS9.4. CRB for Concurrent Association and Tracking (CAT)9.5. Summary: CRB for Intellect and Evolution? 9.6. Appendix: CRB Rule of Thumb for Tracking10. Intelligent Systems Organization: MFT, Genetic Algorithms, and Kant10.1. Kant, MFT, and Intelligent Systems10.2. Emotional Machine (Toward Mathematics of Beauty)10.3. Learning: Genetic Algorithms, MFT, and SemiosisPART THREE: FUTURISTIC DIRECTIONS: FUN STUFF: MIND—PHYSICS + MATHEMATICS + CONJECTURES11. Godel's Theorems, Mind, and Machine11.1. Penrose and Computability of Mathematical Understanding11.2. Logic and Mind11.3. Godel, Turing, Penrose, and Putnam11.4. Godel Theorem vs. Physics of Mind12. Toward Physics of Consciousness12.1. Phenomenology of Consciousness12.2. Physics of Spiritual Substance: Future Directions12.3. EpilogueList of SymbolsDefinitionsBibliographyIndex