%{search_type} search results

• PREFACE; CONTENTS; Part One MATHEMATICAL THEORY; Connectionist Learning Through Gradient Following; INTRODUCTION; CONNECTIONIST SYSTEMS; LEARNING; Supervised Learning vs. Associative Reinforcement Learning; FORMAL ASSUMPTIONS AND NOTATION; BACK-PROPAGATION ALGORITHM FOR SUPERVISED LEARNING; Extended Back-Propagation; REINFORCE ALGORITHMS FOR ASSOCIATIVE REINFORCEMENT LEARNING; Extended REINFORCE Algorithms; DISCUSSION; SUMMARY; REFERENCES; Efficient Stochastic Gradient Learning Algorithm for Neural Network; 1 Introduction; 2 Learning as Stochastic Gradient Descents.

• 3 Convergence Theorems for First Order Schemes4 Convergence of the Second Order Schemes; 5 Discussion; References; INFORMATION STORAGE IN FULLY CONNECTED NETWORKS; 1 INTRODUCTION; 1.1 Neural Networks; 1.2 Organisation; 1.3 Notation; 2 THE MODEL OF McCULLOCH-PITTS; 2.1 State-Theoretic Description; 2.2 Associative Memory; 3 THE OUTER-PRODUCT ALGORITHM; 3.1 The Model; 3.2 Storage Capacity; 4 SPECTRAL ALGORITHMS; 4.1 Outer-Products Revisited; 4.2 Constructive Spectral Approaches; 4.3 Basins of Attraction; 4.4 Choice of Eigenvalues; 5 COMPUTER SIMULATIONS; 6 DISCUSSION; A PROPOSITIONS.

• B OUTER-PRODUCT THEOREMSC PROOFS OF SPECTRAL THEOREMS; References; NEURONIC EQUATIONS AND THEIR SOLUTIONS;
• 1. Introduction; 1
• .1. Reminiscing; 1
• .2. The 1961 Model; 1
• .3. Notation;
• 2. Linear Separable NE; 2
• .1. Neuronic Equations; 2
• .2. Polygonal Inequalities; 2
• .3. Computation of the n-expansion of arbitrary l.s. functions; 2
• .4. Continuous versus discontinuous behaviour: transitions;
• 3. General Boolean NE; 3
• .1. Linearization in tensor space; 3
• .2. Next-state matrix; 3
• .3. Normal modes, attractors; 3
• .4. Synthesis of nets: the inverse problem; 3
• .5. Separable versus Boolean nets.

• Connections with spin formalismReferences; The Dynamics of Searches Directed by Genetic Algorithms; The Hyperplane Transformation.; The Genetic Algorithm as a Hyperplane-Directed Search Procedure; (1) Description of the genetic algorithm; (2) Effects of the S's on the search generated by a genetic algorithm.; (3) An Example.; References.; PROBABILISTIC NEURAL NETWORKS;
• 1. INTRODUCTION;
• 2. MODELING THE NOISY NEURON; 2
• .1. Empirical Properties of Neuron and Synapse;
• 22. Model of Shaw and Vasudevan; 2
• .3. Model of Little; 2
• .4. Model of Taylor.

• 3. NONEQUILIBRIUM STATISTICAL MECHANICS OF LINEAR MODELS3.1. Statistical Law of Motion
• Markov Chain and Master Equation; 3.2. Entropy Production in the Neural; 3.3. Macroscopic Forces and Fluxes; 3.4. Conditions for Thermodynamic Equilibrium; 3.5. Implications for Memory Storage: How Dire?; 4. DYNAMICAL PROPERTIES OF NONLINEAR MODELS; 4.1. Views of Statistical Dynamics; 4.2. Multineuron Interactions, Revisited; 4.3. Cognitive Aspects of the Taylor Model; 4.4. Noisy RAMS and Noisy Nets; 5. THE END OF THE BEGINNING; ACKNOWLEDGMENTS; APPENDIX. TRANSITION PROBABILITIES IN 2-NEURON NETWORKS.

This review volume represents the first attempt to provide a comprehensive overview of this exciting and rapidly evolving development. The book comprises specially commissioned articles by leading researchers in the areas of neural networks and connectionist systems, classifier systems, adaptive network systems, genetic algorithm, cellular automata, artificial immune systems, evolutionary genetics, cognitive science, optical computing, combinatorial optimization, and cybernetics.
(source: Nielsen Book Data)

Building a person has been an elusive goal in artificial intelligence. This failure, John Pollock argues, is because the problems involved are essentially philosophical; what is needed for the construction of a person is a physical system that mimics human rationality. Pollock describes an exciting theory of rationality and its partial implementation in OSCAR, a computer system whose descendants will literally be persons.In developing the philosophical superstructure for this bold undertaking, Pollock defends the conception of man as an intelligent machine and argues that mental states are physical states and persons are physical objects as described in the fable of Oscar, the self conscious machine.Pollock brings a unique blend of philosophy and artificial intelligence to bear on the vexing problem of how to construct a physical system that thinks, is self conscious, has desires, fears, intentions, and a full range of mental states. He brings together an impressive array of technical work in philosophy to drive theory construction in AI. The result is described in his final chapter on "cognitive carpentry." John Pollock is Professor of Philosophy and Cognitive Science at the University of Arizona. A Bradford Book.
(source: Nielsen Book Data)

• An intelligent image-based computer-aided education system: the prototype BIRDS / A.A. David, O. Thiery & M. Crehange
• PLAYMAKER: a knowledge-based approach to characterizing hydrocarbon plays / G. Biswas [and others]
• An expert system for interpreting mesoscale features in oceanographic satellite images / N. Krishnakumar [and others]
• An expert system for tuning particle beam accelerators / D.L. Lager, H.R. Brand & W.J. Maurer
• Expert system approach to assessments of bleeding predispositions in tonsillectomy/adenoidectomy patients / N.J. Pizzi & J.M. Gerrard
• Expert system approach using graph representation and analysis for variable-stroke internal-combustion engine design / S.N.T. Shen, M.S. Chew & G.F. Issa
• A comparison of two new techniques for conceptual clustering / S.L. Crawford & S.K. Souders
• Querying an object-oriented database using free language / P. Trigano [and others]
• Adaptive planning for air combat maneuvering / I.C. Hayslip, J.P. Rosenking & J. Filbert
• AM/AG model: a hierarchical social system metaphor for distributed problem solving / D.G. Shin & J. Leone
• CAUSA
• A tool for model-based knowledge acquisition / W. Dilger & J. Moller
• PRIOPS: a real-time production system architecture for programming and learning in embedded systems / D.E. Parson & G.D. Blank.

This volume contains a well-balanced set of applications and theory papers in artificial intelligence advances. The applications papers each discuss a system that is (or is close to being) a fielded system that solves real problems using one or more AI techniques. They cover areas such as education, physics, energy, control, medicine and mechanical engineering.The theory papers, representing recent advances in various theoretical aspects of AI technology, concern themselves with "building block" issues, i.e. theories, algorithms, architectures, and software tools that can or will be used for modules within future systems. The topics covered are: clustering, natural language, adaptive algorithms, distributed processing, knowledge acquisition, and systems programming.
(source: Nielsen Book Data)

For centuries, people have been fascinated by the possibility of building an artificial system that behaves intelligently. Now there is a new entry in this arena - neural networks. Naturally Intelligent Systems offers a comprehensive introduction to these exciting systems. It provides a technically accurate, yet down-to-earth discussion of neural networks, clearly explaining the underlying concepts of key neural network designs, how they are trained, and why they work. Throughout, the authors present actual applications that illustrate neural networks' utility in the new world.
(source: Nielsen Book Data)
Naturally Intelligent Systems offers a comprehensive introduction to neural networks.
(source: Nielsen Book Data)
For centuries, people have been fascinated by the possibility of building an artificial system that behaves intelligently. From Mary Shelley's Frankenstein monster to the computer intelligence of HAL in 2001, scientists have been cast in the role of creator of such devices. Now there is a new entry into this arena, neural networks, and "Naturally Intelligent Systems explores these systems to see how they work and what they can do. Neural networks are not computers in any traditional sense, and they have little in common with earlier approaches to the problem of fabricating intelligent behavior. Instead, they are information processing systems that are physically modeled after the structure of the brain and that are "trained to perform a task rather than programmed like a computer. Neural networks, in fact, provide a tool with problemsolving capabilities - and limitations - strikingly similar to those of animals and people. In particular, they are successful in applications such as speech, vision, robotics, and pattern recognition. "Naturally Intelligent Systems offers a comprehensive introduction to these exciting systems. It provides a technically accurate, yet down-to-earth discussion of neural networks. No particular mathematical background is necessary; it is written for all interested readers. "Naturally Intelligent Systents clearly explains the underlying concepts of key neural network designs, how they are trained, and why they work. It compares their behavior to the natural intelligence found in animals - and people. Throughout, Caudill and Butler bring the field into focus by presenting actual applications that illustrate neural networks' utility in the real world. MaureenCaudill is President of Adaptics, a neural network consulting company in San Diego and author of the popular "Neural Network Primer" articles that appear regularly in "AI Expert. Charles Butler is a Senior Principal Scientist at Physical Sciences in Alexandria, Virginia. He is a specialist in neural network application development. A Bradford Book.
(source: Nielsen Book Data)

• 1. Neural networks: hopes, problems, and goals
• 2. The loading problem
• 3. Other studies of learning
• 4. The intractability of loading
• 5. Subcases
• 6. Shallow architectures
• 7. Memorization and generalization
• 8. Conclusion.

Using the tools of complexity theory, Stephen Judd develops a formal description of associative learning in connectionist networks. He rigorously exposes the computational difficulties in training neural networks and explores how certain design principles will or will not make the problems easier.Judd looks beyond the scope of any one particular learning rule, at a level above the details of neurons. There he finds new issues that arise when great numbers of neurons are employed and he offers fresh insights into design principles that could guide the construction of artificial and biological neural networks.The first part of the book describes the motivations and goals of the study and relates them to current scientific theory. It provides an overview of the major ideas, formulates the general learning problem with an eye to the computational complexity of the task, reviews current theory on learning, relates the book's model of learning to other models outside the connectionist paradigm, and sets out to examine scale-up issues in connectionist learning.Later chapters prove the intractability of the general case of memorizing in networks, elaborate on implications of this intractability and point out several corollaries applying to various special subcases. Judd refines the distinctive characteristics of the difficulties with families of shallow networks, addresses concerns about the ability of neural networks to generalize, and summarizes the results, implications, and possible extensions of the work. Neural Network Design and the Complexity of Learning is included in the Network Modeling and Connectionism series edited by Jeffrey Elman.
(source: Nielsen Book Data)

Both specialists and laymen will enjoy reading this book. Using a lively, non-technical style and images from everyday life, the authors present the basic principles behind computing and computers. The focus is on those aspects of computation that concern networks of numerous small computational units, whether biological neural networks or artificial electronic devices.
(source: Nielsen Book Data)

• Ch 1. Embedding learning in a general frame-based architecture / T. Tanaka and T.M. Mitchell
• ch. 2. Connectionist learning with Chebychev networks and analyses of its internal representation / A. Narnatame
• ch. 3. Layered inductive learning algorithms and their computational aspects / H. Madala
• ch. 4. An approach to combining explanation-based and neural learning algorithms / J.W. Shavlik and G.G. Towell
• ch. 5. The application of symbolic inductive learning to the acquisition and recognition of noisy texture concepts / P.W. Pachowicz
• ch. 6. Automating technology adaptation in design synthesis / J.R. Kipps and D.D. Gajski
• ch. 7. Connectionist production systems in local and hierarchical representation / A. Sohn and J.-L. Gaudiot
• ch. 8. A parallel architecture for AI nonlinear planning / S. Lee and K. Chung
• ch. 9. Heuristic tree search using nonparametric statistical inference methods / W. Zhang and N.S.V. Rao
• ch. 10. An A* approach to robust plan recognition for intelligent interfaces / R.J. Calistri-Yeh
• ch. 11. Differential A*: an adaptive search method illustrated with robot path planning for moving obstacles & goals, and an uncertain environment / K.I. Trovato
• ch. 12. Path planning under uncertainty / F. Yegenoglu and H.E. Stephanou
• ch. 13. Knowledge-based acquisition in real-time path planning in unknown space / N.G. Bourbakis
• ch. 14. Path planning for two cooperating robot manipulators / Q. Xue and P.C.-Y. Sheu.

Learning and planning are two important topics of artificial intelligence. Learning deals with the algorithmic processes that make a computing machine able to "learn" and improve its performance during the process of complex tasks. Planning on the other hand, deals with decision and construction processes that make a machine capable of constructing an intelligent plan for the solution of a particular complex problem.This book combines both learning and planning methodologies and their applications in different domains. It is divided into two parts. The first part contains seven chapters on the ongoing research work in symbolic and connectionist learning. The second part includes seven chapters which provide the current research efforts in planning methodologies and their application to robotics.
(source: Nielsen Book Data)

• Limited rationality
• execution architectures for decision procedures
• metareasoning architecture
• rational metareasoning
• application to game playing
• application to problem solving search
• learning the value of computation
• toward limited rational agents.
• (source: Nielsen Book Data)

Like Mooki, the hero of Spike Lee's film "Do the Right Thing, " artificially intelligent systems have a hard time knowing what to do in all circumstances. Classical theories of perfect rationality prescribe the "right thing" for any occasion, but no finite agent can compute their prescriptions fast enough. In "Do the Right Thing, " the authors argue that a new theoretical foundation for artificial intelligence can be constructed in which rationality is a property of "programs" within a finite architecture, and their behavior over time in the task environment, rather than a property of individual decisions."Do the Right Thing" suggests that the rich structure that seems to be exhibited by humans, and ought to be exhibited by AI systems, is a necessary result of the pressure for optimal behavior operating within a system of strictly limited resources. It provides an outline for the design of new intelligent systems and describes theoretical and practical tools for bringing about intelligent behavior in finite machines. The tools are applied to game planning and real-time problem solving, with surprising results.Contents Limited Rationality. Execution Architectures for Decision Procedures. Metareasoning Architecture. Rational Metareasoning. Application to Game Playing. Application to Problem Solving Search. Learning the Value of Computation. Toward Limited Rational Agents.
(source: Nielsen Book Data)
Like Mooki, the hero of Spike Lee's film "Do the Right Thing" artificially, intelligent systems have a hard time knowing what to do in all circumstances. Classical theories of perfect rationality prescribe the "right thing" for any occasion, but no finite agent can compute their prescriptions fast enough. In "Do the Right Thing", the authors argue that a new theoretical foundation for artificial intelligence can be constructed in which rationality is a property of "programs" within a finite architecture, and their behaviour over time in the task environment, rather than a property of individual decisions. "Do The Right Thing" suggests that the rich structure that seems to be exhibited by humans, and ought to be exhibited by AI systems, is a necessary result of the pressure for optimal behaviour operating within a system of strictly limited resources. It provides an outline for the design of new intelligent systems and describes theoretical and practical tools for bringing about intelligent behaviour in finite machines. The tools are applied to game planning and real-time problem solving, with surprising results.
(source: Nielsen Book Data)

• AUTHORS' NOTES AND ACKNOWLEDGEMENTS; INTRODUCTION; 1.1. Objectives of this Book; 1.2. The Seeing Eye and the Knowing Eye
• 1 IMAGE AND COMPUTER; 1.1. A Short History; 1.2. The Computer's Eye; 1.3. A Beetle and an Ant-Hill; 1.4. Features and Models; 2 HOW HUMANS SEE THE WORLD; 2.1. The Eye and the Brain; 2.2. The Level of Preattention; 2.3. Right and Left Vision; 2.4. Images and Words; 3 CONVERSATIONS WITH A COMPUTER; 3.1. From a Point to a Region; 3.2. From a Region to an Object; 3.3. From an Object to a Situation; 4 AN APOLOGIA FOR VISION; 4.1. The Evolution of Vision.

• 4
• .2. Vision and Thinking4
• .3. Recollection of the Future; 4
• .4. Cognition through Vision; 5 CREATING A NEW WORLD; 5
• .1. From Elements to the System; 5
• .2. Back to Nature; 5
• .3. Who Do We Think They Are?; CONCLUSIONS; PLATES; REFERENCES; ILLUSTRATIONS; INDEX.

This book considers computer vision to be an integral part of the artificial intelligence system. The core of the book is an analysis of possible approaches to the creation of artificial vision systems, which simulate human visual perception. Much attention is paid to the latest achievements in visual psychology and physiology, the description of the functional and structural organization of the human perception mechanism, the peculiarities of artistic perception and the expression of reality. Computer vision models based on these data are investigated. They include the processes of external data analysis, internal environmental model synthesis, and the generating of behavioristic responses based on external and internal models comparison. Computer vision system evolution resulting from environmental effects is also considered. A unique feature of this book is the authors' use of black and white, and colour prints of traditional and contemporary Russian art to illustrate their principal theses. In doing so, they introduce the reader to a particularly Russian view of the world.
(source: Nielsen Book Data)

• Introduction, C.H. Chen
• combined neural-net/knowledge-based adaptive systems for large scale dynamic control, A.D.C. Holden and S.C. Suddarth
• a connectionist incremental expert system combining production systems and associative memory, H.F. Yin and P. Liang
• optimal hidden units for two-layer nonlinear feedforward networks, T.D. Sanger
• an incremental fine adjustment algorithm for the design of optimal interpolating networks, S.K. Sin and R.J.P. deFigueiredo
• on the asymptotic properties of recurrent neural networks for optimization, J. Wang
• a real-time image segmentation system using a connectionist classifier architecture, W.E. Blanz and S.L. Gish
• segmentation of ultrasonic images with neural network technology's on automatic active sonar classifier development, T.B. Haley
• on the relationships between statistical pattern recognition and artificial neural networks, C.H. Chen.
• (source: Nielsen Book Data)

The revitalization of neural network research in the past few years has already had a great impact on research and development in pattern recognition and artificial intelligence. Although neural network functions are not limited to pattern recognition, there is no doubt that a renewed progress in pattern recognition and its applications now critically depends on neural networks. This volume specially brings together outstanding original research papers in the area and aims to help the continued progress in pattern recognition and its applications.
(source: Nielsen Book Data)

• An introduction to artificial intelligence, N.G. Bourbakis
• fundamental methods for horn logic and AI applications, E. Kounalis and P. Marquis
• applications of genetic algorithms to permutation problems, F. Petry and B. Buckles
• extracting procedural knowledge from software systems using inductive learning in the PM system, R. Reynolds and E. Zannoni
• resource oriented parallel planning, S. Lee and K. Chung
• advanced parsing technology for knowledge based shells, J. Kipps
• analysis and synthesis of intelligent systems, W. Arden
• document analysis and recognition, S.N. Srihari et al
• signal understanding - an AI approach to modulation and classification, J.E. Whelchel et al
• and others.
• (source: Nielsen Book Data)

This volume is the first in a series which deals with the challenge of AI issues, gives updates of AI methods and applications, and promotes high quality new ideas, techniques and methodologies in AI. This volume contains articles by 38 specialists in various AI subfields covering theoretical and application issues.
(source: Nielsen Book Data)

• Ten years of research in artificial intelligence (1957-1967)
• Cognitive simulation (1957-1962)
• Semantic information processing (1962-1967)
• Assumptions underlying persistent optimism
• Biological assumption
• Psychological assumption
• Epistemological assumption
• Ontological assumption
• Alternatives to the traditional assumptions
• The role of the body in intelligent behavior
• The situation: orderly behavior without recourse to rules
• The situation as a function of human needs
• Conclusion: the scope and limits of artificial reason
• The limits of artificial intelligence
• The future of artificial intelligence.

When it was first published in 1972, Hubert Dreyfus's manifesto on the inherent inability of disembodied machines to mimic higher mental functions caused an uproar in the artificial intelligence community. The world has changed since then. Today it is clear that "good old-fashioned AI, " based on the idea of using symbolic representations to produce general intelligence, is in decline (although several believers still pursue its pot of gold), and the focus of the AI community has shifted to more complex models of the mind. It has also become more common for AI researchers to seek out and study philosophy. For this edition of his now classic book, Dreyfus has added a lengthy new introduction outlining these changes and assessing the paradigms of connectionism and neural networks that have transformed the field. At a time when researchers were proposing grand plans for general problem solvers and automatic translation machines, Dreyfus predicted that they would fail because their conception of mental functioning was naive, and he suggested that they would do well to acquaint themselves with modern philosophical approaches to human being. "What Computers Still Can't Do" was widely attacked but quietly studied. Dreyfus's arguments are still provocative and focus our attention once again on what it is that makes human beings unique.
(source: Nielsen Book Data)

• Part 1 Melting the inner code: computational models, syntax, and the folk solids
• connectionism, code, and context
• what networks know
• what networks don't know
• concept, category and prototype. Part 2 From code to process: the presence of a symbol
• the role of representational trajectories
• the cascade of significant virtual machines
• associative learning in a hostile world
• the fate of the folk
• associative engines - the next generation.
• (source: Nielsen Book Data)

Connectionist approaches, Andy Clark argues, are driving cognitive science toward a radical reconception of its explanatory endeavour. At the heart of this reconception lies a shift toward a new and more deeply developmental vision of the mind - a vision that has important implications for the philosophical and psychological understanding of the nature of concepts, of mental causation, and of representational change. Combining philosophical argument, empirical results, and interdisciplinary speculations, Clark charts a fundamental shift from a static, inner-code-oriented conception of the subject matter of cognitive science to a more dynamic, developmentally rich, process-oriented view. Clark argues that this shift makes itself felt in two main ways. First, structured representations are seen as the products of temporally extended cognitive activity and not as the representational bedrock (an innate symbol system or language of thought) upon which all learning is based. Second, the relation between thoughts (as described by folk psychology) and inner computational states is loosened as a result of the fragmented and distributed nature of the connectionist representation of concepts. Other issues Clark raises include the nature of innate knowledge, the conceptual commitments of folk psychology, and the use and abuse of higher-level analyses of connectionist networks.
(source: Nielsen Book Data)

• 1. Introduction and important definitions
• 2. Representation issues
• 3. Perceptron learning and the pocket algorithm
• 4. Winner-take-all groups or linear machines
• 5. Autoassociators and one-shot learning
• 6. Mean squared error (MSE) algorithms
• 7. Unsupervised learning
• 8. The distributed method and radial basis functions
• 9. Computational learning theory and the BRD algorithm
• 10. Constructive algorithms
• 11. Backpropagation
• 12. Backpropagation : variations and applications
• 13. Simulated annealing and boltzmann machines
• 14. Expert systems and neural networks
• 15. Details of the MACIE system
• 16. Noise, redundancy, fault detection, and bayesian decision theory
• 17. Extracting rules from networks.

Neural Network Learning and Expert Systems is the first book to present a unified and in-depth development of neural network learning algorithms and neural network expert systems. Especially suitable for students and researchers in computer science, engineering, and psychology, this text and reference provides a systematic development of neural network learning algorithms from a computational perspective, coupled with an extensive exploration of neural network expert systems which shows how the power of neural network learning can be harnessed to generate expert systems automatically. Features include a comprehensive treatment of the standard learning algorithms (with many proofs), along with much original research on algorithms and expert systems. Additional chapters explore constructive algorithms, introduce computational learning theory, and focus on expert system applications to noisy and redundant problems. For students there is a large collection of exercises, as well as a series of programming projects that lead to an extensive neural network software package. All of the neural network models examined can be implemented using standard programming languages on a microcomputer.
(source: Nielsen Book Data)

• A perspective on the work in this book / Kenneth E. Kinnear, Jr.
• Introduction to genetic programming / John R. Koza
• The evolution of evolvability in genetic programming / Lee Altenberg
• Genetic programming and emergent intelligence / Peter J. Angeline
• Scalable learning in genetic programming using automatic function definition / John R. Koza
• Alternatives in automatic function definition : a comparison of performance / Kenneth E. Kinnear, Jr.
• The donut problem : scalability, generalization and breeding policies in genetic programming / Walter Alden Tackett, Aviram Carmi
• Effects of locality in individual and population evolution / Patrik D'haeseleer, Jason Bluming
• The evolution of mental models / Astro Teller
• Evolution of obstacle avoidance behavior : using noise to promote robust solutions / Craig W. Reynolds
• Pygmies and civil servants / Conor Ryan
• Genetic programming using a minimum decsription length principle / Hitoshi Iba, Hugo de Garis, Taisuke Sato
• Genetic programming in C++: implementation issues / Mike J. Keith, Martin C. Martin. A compiling genetic programming system that directly manipulates the machine code / Peter Nordin
• Automatic generation of programs for crawling and walking / Graham Spencer
• Genetic programming for the acquisition of double auction market strategies / Martin Andrews, Richard Prager
• Two scientific applications of genetic programming : stack filters and non-linear equation fitting to chaotic data / Howard Oakley
• The automatic generation of plans for a mobile robot via genetic programming with automatically defined functions / Simon G. Handley
• Competitively evolving decision trees against fixed training cases for natural language processing / Eric V. Siegel
• Cracking and co-evolving randomizers / Jan Jannink
• Optimizing confidence of text classification by evolution of symbolic expressions / Brij Masand
• Evolvable 3D modeling for model-based object recognition systems / Thang Nguyen, Thomas Huang
• Automatically defined features : the simultaneous evolution of 2-dimensional feature detectors and an algorithm for using them / David Andre
• Genetic micro programming of neural networks / Frédéric Gruau.

Advances in Genetic Programming reports significant results in improving the power of genetic programming, presenting techniques that can be employed immediately in the solution of complex problems in many areas, including machine learning and the simulation of autonomous behavior. Popular languages such as C and C++ are used in manu of the applications and experiments, illustrating how genetic programming is not restricted to symbolic computing languages such as LISP. Researchers interested in getting started in genetic programming will find information on how to begin, on what public-domain code is available, and on how to become part of the active genetic programming community via electronic mail.
(source: Nielsen Book Data)
There is increasing interest in genetic programming by both researchers and professional software developers. These twenty-two invited contributions show how a wide variety of problems across disciplines can be solved using this new paradigm. Advances in Genetic Programming reports significant results in improving the power of genetic programming, presenting techniques that can be employed immediately in the solution of complex problems in many areas, including machine learning and the simulation of autonomous behavior. Popular languages such as C and C++ are used in many of the applications and experiments, illustrating how genetic programming is not restricted to symbolic computing languages such as LISP. Researchers interested in getting started in genetic programming will find information on how to begin, on what public domain code is available, and on how to become part of the active genetic programming community via electronic mail. A major focus of the book is on improving the power of genetic programming. Experimental results are presented in a variety of areas, including adding memory to genetic programming, using locality and "demes" to maintain evolutionary diversity, avoiding the traps of local optima by using coevolution, using noise to increase generality, and limiting the size of evolved solutions to improve generality. Significant theoretical results in the understanding of the processes underlying genetic programming are presented, as are several results in the area of automatic function definition. Performance increases are demonstrated by directly evolving machine code, and implementation and design issues for genetic programming in C++ are discussed.
(source: Nielsen Book Data)

• Computers and computation
• the discrete neuron
• the Boolean neuron
• alternating circuits
• small, shallow alternating circuits
• threshold circuits
• cyclic networks
• probabilistic neural networks.
• (source: Nielsen Book Data)

Neural networks usually work adequately on small problems but can run into trouble when they are scaled up to problems involving large amounts of input data. Circuit Complexity and Neural Networks addresses the important question of how well neural networks scale - that is, how fast the computation time and number of neurons grow as the problem size increases. It surveys recent research in circuit complexity (a robust branch of theoretical computer science) and applies this work to a theoretical understanding of the problem of scalability.Most research in neural networks focuses on learning, yet it is important to understand the physical limitations of the network before the resources needed to solve a certain problem can be calculated. One of the aims of this book is to compare the complexity of neural networks and the complexity of conventional computers, looking at the computational ability and resources (neurons and time) that are a necessary part of the foundations of neural network learning.Circuit Complexity and Neural Networks contains a significant amount of background material on conventional complexity theory that will enable neural network scientists to learn about how complexity theory applies to their discipline, and allow complexity theorists to see how their discipline applies to neural networks.
(source: Nielsen Book Data)
Neural networks usually work adequately on small problems but can run into trouble when they are scaled up to problems involving large amounts of input data. Circuit Complexity and Neural Networks addresses the important question of how well neural networks scale - that is, how fast the computation time and number of neurons grow as the problem size increases. It surveys recent research in circuit complexity (a robust branch of theoretical computer science) and applies this work to a theoretical understanding of the problem of scalability.
(source: Nielsen Book Data)

• The probably approximately correct learning model
• Occam's razor
• the Vapnik-Chervonenkis dimension
• weak and strong learning
• learning in the presence of noise
• inherent unpredictability
• reducibility in PAC learning
• learning finite automata by experimentation
• appendix - some tools for probabilistic analysis.
• (source: Nielsen Book Data)

Emphasizing issues of computational efficiency, Michael Kearns and Umesh Vazirani introduce a number of central topics in computational learning theory for researchers and students in artificial intelligence, neural networks, theoretical computer science, and statistics. Emphasizing issues of computational efficiency, Michael Kearns and Umesh Vazirani introduce a number of central topics in computational learning theory for researchers and students in artificial intelligence, neural networks, theoretical computer science, and statistics. Computational learning theory is a new and rapidly expanding area of research that examines formal models of induction with the goals of discovering the common methods underlying efficient learning algorithms and identifying the computational impediments to learning. Each topic in the book has been chosen to elucidate a general principle, which is explored in a precise formal setting. Intuition has been emphasized in the presentation to make the material accessible to the nontheoretician while still providing precise arguments for the specialist. This balance is the result of new proofs of established theorems, and new presentations of the standard proofs. The topics covered include the motivation, definitions, and fundamental results, both positive and negative, for the widely studied L. G. Valiant model of Probably Approximately Correct Learning; Occam's Razor, which formalizes a relationship between learning and data compression; the Vapnik-Chervonenkis dimension; the equivalence of weak and strong learning; efficient learning in the presence of noise by the method of statistical queries; relationships between learning and cryptography, and the resulting computational limitations on efficient learning; reducibility between learning problems; and algorithms for learning finite automata from active experimentation.
(source: Nielsen Book Data)