%{search_type} search results

• 1. Introduction
• 2. Probabilistic inference in graphical models
• 3. Pattern classification
• 4. Unsupervised learning
• 5. Fata compression
• 6. Vhannel coding
• 7. Future research directions.

A variety of problems in machine learning and digital communication deal with complex but structured natural or artificial systems. In this book, Brendan Frey uses graphical models as an overarching framework to describe and solve problems of pattern classification, unsupervised learning, data compression, and channel coding. Using probabilistic structures such as Bayesian belief networks and Markov random fields, he is able to describe the relationships between random variables in these systems and to apply graph-based inference techniques to develop algorithms. Among the algorithms described are the wake-sleep algorithm for unsupervised learning, the iterative turbodecoding algorithm, the bits-back coding method, the Markov chain Monte Carlo technique, and variational inference.
(source: Nielsen Book Data)
A variety of problems in machine learning and digital communication deal with complex but structured natural or artificial systems. In this book, Brendan J. Frey uses graphical models as an overarching framework to describe and solve problems of pattern classification, unsupervised learning, data compression, and channel coding. Using probabilistic structures such as Bayesian belief networks and Markov random fields, he is able to describe the relationships between random variables in these systems and to apply graph-based inference techniques to develop new algorithms.
(source: Nielsen Book Data)

• Bianchini, Frasconi, Gori, and Maggini, Optimal Learning in Artificial Neural Networks: A Theoretical View. Kanjilal, Orthogonal Transformation Techniques in the Optimization of Feedforward Neural Network Systems. Museli, Sequential Constructive Techniques. Yu, Xu, and Wang, Fast Backpropagation Training Using Optimal Learning Rate and Momentum. Angulo and Torras, Learning of Nonstationary Processes. Schaller, Constraint Satisfaction Problems. Yang and Chen, Dominant Neuron Techniques. Lin, Chiang, and Kim, CMAC-based Techniques for Adaptive Learning Control. Deco, Information Dynamics and Neural Techniques for Data Analysis. Gorinevsky, Radial Basis Function Network Approximation and Learning in Task-Dependent Feedforward Control of Nonlinear Dynamical Systems.
• (source: Nielsen Book Data)

This volume covers practical and effective implementation techniques, including recurrent methods, Boltzmann machines, constructive learning with methods for the reduction of complexity in neural network systems, modular systems, associative memory, neural network design based on the concept of the Inductive Logic Unit, and a comprehensive treatment of implementations in the area of data classification. Numerous examples enhance the text. Practitioners, researchers, and students in engineering and computer science will find Implementation Techniques a comprehensive and powerful reference.
(source: Nielsen Book Data)

• Albertini and Pra, Recurrent Neural Networks: Identification and Other System Theoretic Properties. Anderson and Titterington, Boltzmann Machines: Statistical Associations and Algorithms for Training Anderson and Titterington. Campbell, Constructive Learning Techniques for Designing Neural Network Systems. Mehrotra and Mohan, Modular Neural Networks. Xu and Kwong, Associative Memories. Fry and Sova, A Logical Basis for Neural Network Design.Hoekstra, Duin, and Kraaijveld, Neural Networks Applied to Data Analysis. Zhang and Wang, Multi-Mode Single Neuron Arithmetics.
• (source: Nielsen Book Data)

Optimization Techniques is a unique reference source to a diverse array of methods for achieving optimization, and includes both systems structures and computational methods. The text devotes broad coverage toa unified view of optimal learning, orthogonal transformation techniques, sequential constructive techniques, fast back propagation algorithms, techniques for neural networks with nonstationary or dynamic outputs, applications to constraint satisfaction, optimization issues and techniques for unsupervised learning neural networks, optimum Cerebellar Model of Articulation Controller systems, a new statistical theory of optimum neural learning, and the role of the Radial Basis Function in nonlinear dynamical systems.This volume is useful for practitioners, researchers, and students in industrial, manufacturing, mechanical, electrical, and computer engineering.
(source: Nielsen Book Data)

• Contributors
• Acknowledgments
• 1. An Introduction to the Third Volume / Lee Spector, William B. Langdon, Una-May O'Reilly, Peter J. Angelino
• I. Applications
• 2. An Automatic Software Re-Engineering Tool Based on Genetic Programming / Conor Ryan and Laur Ivan
• 3. CAD Surface Reconstruction from Digitized 3D Point Data with a Genetic Programming/Evolution Strategy Hybrid / Robert E. Keller, Wolfgang Banzhaf, Jorn Mehnen and Klaus Weinert
• 4. A Genetic Programming Approach for Robust Language Interpretation / Carolyn Penstein Rose
• 5. Time Series Modeling Using Genetic Programming: An Application to Rainfall-Runoff Models / Peter A. Whigham and Peter F. Crapper
• 6. Automatic Synthesis, Placement, and Routing of Electrical Circuits by Means of Genetic Programming / John R. Koza and Forest H. Bennett III
• 7. Quantum Computing Applications of Genetic Programming / Lee Spector, Howard Barnum, Herbert J. Bernstein and Nikhil Swamy
• II. Theory
• II. Theory
• 8. The Evolution of Size and Shape / William B. Langdon, Terry Soule, Riccardo Poli and James A. Foster
• 9. Fitness Distributions: Tools for Designing Efficient Evolutionary Computations / Christian Igel and Kumar Chellapilla
• 10. Analysis of Single-Node (Building) Blocks in Genetic Programming / Jason M. Daida, Robert R. Bertram, John A. Polito 2 and Stephen A. Stanhope
• 11. Rooted-Tree Schemata in Genetic Programming / Justinian P. Rosca and Dana H. Ballard
• III. Extensions
• III. Extensions
• 12. Efficient Evolution of Machine Code for CISC Architectures Using Instruction Blocks and Homologous Crossover / Peter Nordin, Wolfgang Banzhaf and Frank D. Francone
• 13. Sub-machine-code Genetic Programming / Riccardo Poli and William B. Langdon
• 14. The Internal Reinforcement of Evolving Algorithms / Astro Teller
• 15. Inductive Genetic Programming with Immune Network Dynamics / Nikolay I. Nikolaev, Hitoshi Iba and Vanio Slavov
• 16. A Self-Tuning Mechanism for Depth-Dependent Crossover / Takuyo Ito, Hitoshi Iba and Satoshi Sato
• 17. Genetic Recursive Regression for Modeling and Forecasting Real-World Chaotic Time Series / Geum Yong Lee
• 18. Co-evolutionary Fitness Switching: Learning Complex Collective Behaviors Using Genetic Programming / Byoung-Tak Zhang and Dong-Yeon Cho
• 19. Evolving Multiple Agents by Genetic Programming / Hitoshi Iba
• Index.

Genetic programming is a form of evolutionary computation that evolves programs and program-like executable structures for developing reliable time-and cost-effective applications. It does this by breeding programs over many generations, using the principles of natural selection, sexual recombination, and mutuation. This third volume of Advances in Genetic Programming highlights many of the recent technical advances in this increasingly popular field. Genetic programming is a form of evolutionary computation that evolves programs and program-like executable structures for developing reliable time-and cost-effective applications. It does this by breeding programs over many generations, using the principles of natural selection, sexual recombination, and mutuation. This third volume of Advances in Genetic Programming highlights many of the recent technical advances in this increasingly popular field.
(source: Nielsen Book Data)
Genetic programming is a form of evolutionary computation that evolves programs and program-like executable structures for developing reliable time -- and cost-effective applications. It does this by breeding programs over many generations, using the principles of natural selection, sexual recombination, and mutuation. This third volume of "Advances in Genetic Programming" highlights many of the recent technical advances in this increasingly popular field.
(source: Nielsen Book Data)

• Introduction to support vector learning
• roadmap. Part 1 Theory: three remarks on the support vector method of function estimation, Vladimir Vapnik
• generalization performance of support vector machines and other pattern classifiers, Peter Bartlett and John Shawe-Taylor
• Bayesian voting schemes and large margin classifiers, Nello Cristianini and John Shawe-Taylor
• support vector machines, reproducing kernel Hilbert spaces, and randomized GACV, Grace Wahba
• geometry and invariance in kernel based methods, Christopher J.C. Burges
• on the annealed VC entropy for margin classifiers - a statistical mechanics study, Manfred Opper
• entropy numbers, operators and support vector kernels, Robert C. Williamson et al. Part 2 Implementations: solving the quadratic programming problem arising in support vector classification, Linda Kaufman
• making large-scale support vector machine learning practical, Thorsten Joachims
• fast training of support vector machines using sequential minimal optimization, John C. Platt. Part 3 Applications: support vector machines for dynamic reconstruction of a chaotic system, Davide Mattera and Simon Haykin
• using support vector machines for time series prediction, Klaus-Robert Muller et al
• pairwise classification and support vector machines, Ulrich Kressel. Part 4 Extensions of the algorithm: reducing the run-time complexity in support vector machines, Edgar E. Osuna and Federico Girosi
• support vector regression with ANOVA decomposition kernels, Mark O. Stitson et al
• support vector density estimation, Jason Weston et al
• combining support vector and mathematical programming methods for classification, Bernhard Scholkopf et al.
• (source: Nielsen Book Data)

The Support Vector Machine is a powerful new learning algorithm for solving a variety of learning and function estimation problems, such as pattern recognition, regression estimation, and operator inversion. The impetus for this collection was a workshop on Support Vector Machines held at the 1997 NIPS conference. The contributors, both university researchers and engineers developing applications for the corporate world, form a Who's Who of this exciting new area.ContributorsPeter Bartlett, Kristin P. Bennett, Christopher J.C. Burges, Nello Cristianini, Alex Gammerman, Federico Girosi, Simon Haykin, Thorsten Joachims, Linda Kaufman, Jens Kohlmorgen, Ulrich Kressel, Davide Mattera, Klaus-Robert Muller, Manfred Opper, Edgar E. Osuna, John C. Platt, Gunnar Ratsch, Bernhard Schoelkopf, John Shawe-Taylor, Alexander J. Smola, Mark O. Stitson, Vladimir Vapnik, Volodya Vovk, Grace Wahba, Chris Watkins, Jason Weston, Robert C. Williamson.
(source: Nielsen Book Data)
The Support Vector Machine is a powerful new learning algorithm for solving a variety of learning and function estimation problems, such as pattern recognition, regression estimation, and operator inversion. The impetus for this collection was a workshop on Support Vector Machines held at the 1997 NIPS conference. The contributors, both university researchers and engineers developing applications for the corporate world, form a Who's Who of this exciting new area.
(source: Nielsen Book Data)

• Introduction - background material
• the building blocks
• the April++ language - AprilO - adding objects to April
• AprilQ - the database extension
• April++ - objects with knowledge base state
• the implementation of April++
• the applications - component based agent construction
• an agent for multi-service network management.
• (source: Nielsen Book Data)

Advances in computer technology in general and computer networks in particular have significantly affected the requirements of modern applications, where the need to operate in decentralised environments is of primary importance. The conceptual models of the applications are also becoming complex and semantically rich.A promising technology towards the design and development of systems of such domains is agent based systems. Agents, having a knowledge component, act and interact with other agents and information sources in order to achieve some goals. Platforms intended for supporting the development of such systems should offer a number of features, including communication, concurrency, mobility, high level data structures, object orientation etc.This book describes the design and implementation of such a language platform called April++ and its use on a number of applications. Methodologically, in designing and implementing the language, a layered approach has been adopted. April++ has been developed as a series of macro defined layers on top of the relatively primitive features of a pre-existing language called April.On top of April++, an agent layer has been built (as a set of pre-defined classes) for constructing agent based systems. This layer has been customised for specific application domains considered. This includes a mobile agent application, a distributed database application and a network management one.
(source: Nielsen Book Data)

• Introduction - background material
• the building blocks
• the April++ language - AprilO - adding objects to April
• AprilQ - the database extension
• April++ - objects with knowledge base state
• the implementation of April++
• the applications - component based agent construction
• an agent for multi-service network management.
• (source: Nielsen Book Data)

Advances in computer technology in general and computer networks in particular have significantly affected the requirements of modern applications, where the need to operate in decentralised environments is of primary importance. The conceptual models of the applications are also becoming complex and semantically rich.A promising technology towards the design and development of systems of such domains is agent based systems. Agents, having a knowledge component, act and interact with other agents and information sources in order to achieve some goals. Platforms intended for supporting the development of such systems should offer a number of features, including communication, concurrency, mobility, high level data structures, object orientation etc.This book describes the design and implementation of such a language platform called April++ and its use on a number of applications. Methodologically, in designing and implementing the language, a layered approach has been adopted. April++ has been developed as a series of macro defined layers on top of the relatively primitive features of a pre-existing language called April.On top of April++, an agent layer has been built (as a set of pre-defined classes) for constructing agent based systems. This layer has been customised for specific application domains considered. This includes a mobile agent application, a distributed database application and a network management one.
(source: Nielsen Book Data)

• Machine generated contents note: Open Sesame?: Fifteen Variations on the Theme of Openness in Learning Environments / J. Self
• Cognitive Applications of New Computational Technologies in Eye Tracking / S.P. Marshall
• Collaborative Learning in Open Distributed Environments -- Pedagogical Principles and Computational Methods / H.U. Hoppe
• Overview of the State of the Art in ITS Authoring Tools / T. Murray
• Trends and Issues in AI and Education: Towards a Common Research Framework / J. Sandberg
• Agent Systems for Diversity in Human Learning / J. Les / G. Cumming / S. Finch
• Teachable Agents: Combining Insights from Learning Theory and Computer Science / S. Brophy / G. Biswas / T. Katzlberger / [and others]
• Meta-knowledge Representation for Learning Scenarios Engineering / G. Paquette
• Multi-Agent Design of a Peer-Help Environment / J. Vassileva / J. Greer / G. McCalla / [and others]
• Methodology for Building Intelligent Educational Agents / H.N. Keeling
• Systemion: A New Agent Model to Design Intelligent Tutoring Systems / M.F. Canut / G. Gouarderes / E. Sanchis
• Learning Goal Ontology Supported by Learning Theories for Opportunistic Group Formation / T. Supnithi / A. Inaba / M. Ikeda / [and others]
• Toward Intelligent Analysis and Support of Collaborative Learning Interaction / A. Soller / F. Linton / B. Goodman / [and others]
• Ontology-Aware Authoring Tool: Functional Structure and Guidance Generation / L. Jin / W. Chen / Y. Hayashi / [and others]
• Formatively Evaluating REDEEM -- An Authoring Environment for ITSs / S. Ainsworth / J. Underwood / S. Grimshaw
• Intelligent Agent Instructional Design Tool for a Hypermedia Design Course / S. Stoyanov / L. Aroyo / P. Kommers.

Annotation This volume will be the proceedings for the 9th International Conference on Artificial Intelligence in Education (AI-ED 1999). This is one of a series of international conferences in this area and it is designed to report on state of the art research in the field of AI in Education. This field is interdisciplinary and brings together researchers from the domains of computer science, cognitive science, education, psychology, linguistics, and engineering (to name a few). Researchers will contribute manuscripts to this volume, providing opportunities for cross-fertilization of information across disciplines that will lead to advances and new applications in the field. New computational technologies will be described that support learning, exploration, and collaboration. Technologies can support both the individual and small groups of individuals who work collaboratively to solve problems and learn new materials. New methodologies for supporting and documenting the learning process in both these situations are being developed and are described in this volume.

• pt. I. Technology. Robust layered control system for a mobile robot
• Robot that walks: emergent behaviors from a carefully evolved network
• Learning a distributed map representation based on navigation behaviors
• New approaches to robotics. pt. II. Philosophy. Intelligence without representation
• Planning is just a way of avoiding figuring out what to do next
• Elephants don't play chess
• Intelligence without reason.

Until the mid-1980s, AI researchers assumed that an intelligent system doing high-level reasoning was necessary for the coupling of perception and action. In this traditional model, cognition mediates between perception and plans of action. Realizing that this core AI, as it was known, was illusory, Rodney A. Brooks turned the field of AI on its head by introducing the behavior-based approach to robotics. The cornerstone of behavior-based robotics is the realization that the coupling of perception and action gives rise to all the power of intelligence and that cognition is only in the eye of an observer. Behavior-based robotics has been the basis of successful applications in entertainment, service industries, agriculture, mining, and the home. It has given rise to both autonomous mobile robots and more recent humanoid robots such as Brooks' Cog. This book represents Brooks' initial formulation of and contributions to the development of the behavior-based approach to robotics. It presents all of the key philosophical and technical ideas that put this "bottom-up" approach at the forefront of current research in not only AI but all of cognitive science.
(source: Nielsen Book Data)

• An introduction to evolutionary computation
• evolutionary algorithms as search algorithms
• theoretical analysis of evolutionary algorithms
• advanced search operators in evolutionary algorithms
• parallel evolutionary algorithms
• a comparison of simulated annealing and an evolutionary algorithm on traveling salesman problems
• power system design and management by evolutionary algorithms
• telecommunications network design and management by evolutionary algorithms
• an optimization tool based on evolutionary algorithms
• the evolution of artificial neural network architectures
• an experimental study of generalization in evolutionary learning
• an evolutionary approach to the N-person prisoner's dilemma game
• automated design and generalisation of heuristics
• high-order credit assignment in classifier systems.
• (source: Nielsen Book Data)

Evolutionary computation is the study of computational systems which use ideas and get inspiration from natural evolution and adaptation. This book is devoted to the theory and application of evolutionary computation. It is a self-contained volume which covers both introductory material and selected advanced topics. The book can roughly be divided into two major parts: the introductory one and the one on selected advanced topics. Each part consists of several chapters which present an in-depth discussion of selected topics. A strong connection is established between evolutionary algorithms and traditional search algorithms. This connection enables us to incorporate ideas in more established fields into evolutionary algorithms. The book is aimed at a wide range of readers. It does not require previous exposure to the field since introductory material is included. It will be of interest to anyone who is interested in adaptive optimization and learning. People in computer science, artificial intelligence, operations research, and various engineering fields will find it particularly interesting.
(source: Nielsen Book Data)

• Cortical images, self-organising neural networks and object classification / Nikolay Petkov
• Parallel implementation of a neural network ensemble on the connection machine / Daijin Kim, Minsoo Suk
• Boolean neural networks trained with simulated annealing / Jarkko Niittylahti
• On the computational complexity of analyzing the Hopfield-Clique network / Arun Jagota
• A harmony-maximisation network implementation of a compound labeling scheme for scene analysis / Tatiana Tambouratzis
• Optimal image boundary via Hopfield net and tunneling / William Cheung, Roland Chin, Tong Lee
• Shape matching based on invariants / Stan Z. Li.

• Neural networks in systems identification and control - supervised learning in multilayer perceptions - the back-propagation algorithm
• identification of two-dimensional state space discrete systems using neural networks
• neural networks for control
• neuro-based adaptive regulator
• local model networks and self-tuning predictive control
• fuzzy and neuro-fuzzy systems in modelling, control and robot path planning - an on-line self constructing fuzzy modelling architecture based on neural and fuzzy concepts and techniques
• neuro-fuzzy model-based control
• fuzzy and neurofuzzy approaches to mobile robot path and motion planning under uncertainty
• genetic-evolutionary algorithms - a tutorial overview of genetic algorithms and their applications
• results from a variety of genetic algorithm applications showing the robustness of the approach
• evolutionary algorithms in computer-aided design of integrated circuits
• soft computing applications - soft data fusion
• application of neural networks to computer gaming
• coherent neural networks and their applications to control and signal processing
• neural, fuzzy and evolutionary reinforcement learning systems - an application case study
• neural networks in industrial and environmental applications.
• (source: Nielsen Book Data)

Soft computing is a branch of computing which, unlike hard computing, can deal with uncertain, imprecise and inexact data. The three constituents of soft computing are fuzzy-logic-based computing, neurocomputing, and genetic algorithms. Fuzzy logic contributes the capability of approximate reasoning, neurocomputing offers function approximation and learning capabilities, and genetic algorithms provide a methodology for systematic random search and optimization. These three capabilities are combined in a complementary and synergetic fashion.This book presents a cohesive set of contributions dealing with important issues and applications of soft computing in systems and control technology. The contributions include state-of-the-art material, mathematical developments, fresh results, and how-to-do issues. Among the problems studied via neural, fuzzy, neurofuzzy and genetic methodologies are: data fusion, reinforcement learning, approximation properties, multichannel imaging, signal processing, system optimization, gaming, and several forms of control.The book can serve as a reference for researchers and practitioners in the field. Readers can find in it a large amount of useful and timely information, and thus save considerable effort in searching for other scattered literature.
(source: Nielsen Book Data)

• Ch. 1. Introduction
• Ch. 2. Ant Foraging Behavior, Combinatorial Optimization, and Routing in Communications Network
• Ch. 3. Division of Labor and Task Allocation
• Ch. 4. Cemetery Organization, Brood Sorting, Data Analysis, and Graph Partitioning
• Ch. 5. Self-Organization and Templates: Application to Data Analysis and Graph Partitioning
• Ch. 6. Nest Building and Self-Assembling
• Ch. 7. Cooperative Transport by Insects and Robots
• Ch. 8. Epilogue.

Social insects-ants, bees, termites, and wasps-can be viewed as powerful problem-solving systems with sophisticated collective intelligence. Composed of simple interacting agents, this intelligence lies in the networks of interactions among individuals and between individuals and the environment. A fascinating subject, social insects are also a powerful metaphor for artificial intelligence, and the problems they solve-finding food, dividing labor among nestmates, building nests, responding to external challenges-have important counterparts in engineering and computer science. This book provides a detailed look at models of social insect behaviour and how to apply these models in the design of complex systems. The book shows how these models replace an emphasis on control, preprogramming, and centralization with designs featuring autonomy, emergence, and distributed functioning. These designs are proving immensely flexible and robust, able to adapt quickly to changing environments and to continue functioning even when individual elements fail. In particular, these designs are an exciting approach to the tremendous growth of complexity in software and information. Swarm Intelligence draws on up-to-date research from biology, neuroscience, artificial intelligence, robotics, operations research, and computer graphics, and each chapter is organized around a particular biological example, which is then used to develop an algorithm, a multiagent system, or a group of robots. The book will be an invaluable resource for a broad range of disciplines.
(source: Nielsen Book Data)

• The Study of Intelligence--Foundations and Issues
• The Study of Intelligence
• Characterizing Intelligence
• Studying Intelligence: The Synthetic Approach
• Foundations of Classical Artificial Intelligence and Cognitive Science
• Cognitive Science: Preliminaries
• The Cognitivistic Paradigm
• An Architecture for an Intelligent Agent
• The Fundamental Problems of Classical Al and Cognitive Science
• Real Worlds versus Virtual Worlds
• Some Well-Known Problems with Classical Systems
• The Fundamental Problems of Classical Al
• Remedies and Alternatives
• A Framework for Embodied Cognitive Science
• Embodied Cognitive Science: Basic Concepts
• Complete Autonomous Agents
• Biological and Artificial Agents
• Designing for Emergence--Logic-Based and Embodied Systems
• Explaining Behavior
• Neural Networks for Adaptive Behavior
• From Biological to Artificial Neural Networks
• The Four or Five Basics
• Distributed Adaptive Control
• Types of Neural Networks
• Beyond Information Processing: A Polemic Digression
• Approaches and Agent Examples
• Braitenberg Vehicles
• Motivation
• The Fourteen Vehicles
• Segmentation of Behavior and the Extended Braitenberg Architecture
• The Subsumption Architecture
• Behavior-Based Robotics
• Designing a Subsumption-Based Robot
• Examples of Subsumption-Based Architectures
• Conclusions: The Subsumption Approach to Designing Intelligent Systems
• Artificial Evolution and Artificial Life.

By the mid-1980s researchers from artificial intelligence, computer science, brain and cognitive science, and psychology realized that the idea of computers as intelligent machines was inappropriate. The brain does not run "programs"; it does something entirely different. But what? Evolutionary theory says that the brain has evolved not to do mathematical proofs but to control our behavior, to ensure our survival. Researchers now agree that intelligence always manifests itself in behavior -- thus it is behavior that we must understand. An exciting new field has grown around the study of behavior-based intelligence, also known as embodied cognitive science, "new AI, " and "behavior-based AI." This book provides a systematic introduction to this new way of thinking. After discussing concepts and approaches such as subsumption architecture, Braitenberg vehicles, evolutionary robotics, artificial life, self-organization, and learning, the authors derive a set of principles and a coherent framework for the study of naturally and artificially intelligent systems, or autonomous agents. This framework is based on a synthetic methodology whose goal is understanding by designing and building. The book includes all the background material required to understand the principles underlying intelligence, as well as enough detailed information on intelligent robotics and simulated agents so readers can begin experiments and projects on their own. The reader is guided through a series of case studies that illustrate the design principles of embodied cognitive science.
(source: Nielsen Book Data)
Evolutionary theory says that the brain has evolved not to do mathematical proofs but to control behaviour and ensure survival. Researchers agree that intelligence always manifests itself in behaviour - thus it is behaviour that must be understood. A new field has grown around the study of behaviour-based intelligence, also known as embodied cognitive science, "new AI" and "behaviour-based AI". This book provides a systematic introduction to this new way of thinking. After discussing concepts and approaches such as subsumption architecture, Braitenberg vehicles, evolutionary robotics, artificial life, self-organization and learning, the authors derive a set of principles and a framework for the study of naturally and artificially intelligent systems, or autonomous agents. This framework is based on a synthetic methodology whose goal is understanding by designing and building. The text includes the background material required to understand the principles underlying intelligence, as well as information of intelligent robotics and simulated agents so readers can begin experiments and projects on their own. The reader is guided through a series of case studies that illustrate the design principles of embodied cognitive science.
(source: Nielsen Book Data)

• The Study of Intelligence--Foundations and Issues
• The Study of Intelligence
• Characterizing Intelligence
• Studying Intelligence: The Synthetic Approach
• Foundations of Classical Artificial Intelligence and Cognitive Science
• Cognitive Science: Preliminaries
• The Cognitivistic Paradigm
• An Architecture for an Intelligent Agent
• The Fundamental Problems of Classical Al and Cognitive Science
• Real Worlds versus Virtual Worlds
• Some Well-Known Problems with Classical Systems
• The Fundamental Problems of Classical Al
• Remedies and Alternatives
• A Framework for Embodied Cognitive Science
• Embodied Cognitive Science: Basic Concepts
• Complete Autonomous Agents
• Biological and Artificial Agents
• Designing for Emergence--Logic-Based and Embodied Systems
• Explaining Behavior
• Neural Networks for Adaptive Behavior
• From Biological to Artificial Neural Networks
• The Four or Five Basics
• Distributed Adaptive Control
• Types of Neural Networks
• Beyond Information Processing: A Polemic Digression
• Approaches and Agent Examples
• Braitenberg Vehicles
• Motivation
• The Fourteen Vehicles
• Segmentation of Behavior and the Extended Braitenberg Architecture
• The Subsumption Architecture
• Behavior-Based Robotics
• Designing a Subsumption-Based Robot
• Examples of Subsumption-Based Architectures
• Conclusions: The Subsumption Approach to Designing Intelligent Systems
• Artificial Evolution and Artificial Life.

Evolutionary theory says that the brain has evolved not to do mathematical proofs but to control behaviour and ensure survival. Researchers agree that intelligence always manifests itself in behaviour - thus it is behaviour that must be understood. A new field has grown around the study of behaviour-based intelligence, also known as embodied cognitive science, "new AI" and "behaviour-based AI". This book provides a systematic introduction to this new way of thinking. After discussing concepts and approaches such as subsumption architecture, Braitenberg vehicles, evolutionary robotics, artificial life, self-organization and learning, the authors derive a set of principles and a framework for the study of naturally and artificially intelligent systems, or autonomous agents. This framework is based on a synthetic methodology whose goal is understanding by designing and building. The text includes the background material required to understand the principles underlying intelligence, as well as information of intelligent robotics and simulated agents so readers can begin experiments and projects on their own. The reader is guided through a series of case studies that illustrate the design principles of embodied cognitive science.
(source: Nielsen Book Data)
By the mid-1980s researchers from artificial intelligence, computer science, brain and cognitive science, and psychology realized that the idea of computers as intelligent machines was inappropriate. The brain does not run "programs"; it does something entirely different. But what? Evolutionary theory says that the brain has evolved not to do mathematical proofs but to control our behavior, to ensure our survival. Researchers now agree that intelligence always manifests itself in behavior--thus it is behavior that we must understand. An exciting new field has grown around the study of behavior-based intelligence, also known as embodied cognitive science, "new AI, " and "behavior-based AI."This book provides a systematic introduction to this new way of thinking. After discussing concepts and approaches such as subsumption architecture, Braitenberg vehicles, evolutionary robotics, artificial life, self-organization, and learning, the authors derive a set of principles and a coherent framework for the study of naturally and artificially intelligent systems, or autonomous agents. This framework is based on a synthetic methodology whose goal is understanding by designing and building.The book includes all the background material required to understand the principles underlying intelligence, as well as enough detailed information on intelligent robotics and simulated agents so readers can begin experiments and projects on their own. The reader is guided through a series of case studies that illustrate the design principles of embodied cognitive science.
(source: Nielsen Book Data)

• The Study of Intelligence--Foundations and Issues
• The Study of Intelligence
• Characterizing Intelligence
• Studying Intelligence: The Synthetic Approach
• Foundations of Classical Artificial Intelligence and Cognitive Science
• Cognitive Science: Preliminaries
• The Cognitivistic Paradigm
• An Architecture for an Intelligent Agent
• The Fundamental Problems of Classical Al and Cognitive Science
• Real Worlds versus Virtual Worlds
• Some Well-Known Problems with Classical Systems
• The Fundamental Problems of Classical Al
• Remedies and Alternatives
• A Framework for Embodied Cognitive Science
• Embodied Cognitive Science: Basic Concepts
• Complete Autonomous Agents
• Biological and Artificial Agents
• Designing for Emergence--Logic-Based and Embodied Systems
• Explaining Behavior
• Neural Networks for Adaptive Behavior
• From Biological to Artificial Neural Networks
• The Four or Five Basics
• Distributed Adaptive Control
• Types of Neural Networks
• Beyond Information Processing: A Polemic Digression
• Approaches and Agent Examples
• Braitenberg Vehicles
• Motivation
• The Fourteen Vehicles
• Segmentation of Behavior and the Extended Braitenberg Architecture
• The Subsumption Architecture
• Behavior-Based Robotics
• Designing a Subsumption-Based Robot
• Examples of Subsumption-Based Architectures
• Conclusions: The Subsumption Approach to Designing Intelligent Systems
• Artificial Evolution and Artificial Life.

Evolutionary theory says that the brain has evolved not to do mathematical proofs but to control behaviour and ensure survival. Researchers agree that intelligence always manifests itself in behaviour - thus it is behaviour that must be understood. A new field has grown around the study of behaviour-based intelligence, also known as embodied cognitive science, "new AI" and "behaviour-based AI". This book provides a systematic introduction to this new way of thinking. After discussing concepts and approaches such as subsumption architecture, Braitenberg vehicles, evolutionary robotics, artificial life, self-organization and learning, the authors derive a set of principles and a framework for the study of naturally and artificially intelligent systems, or autonomous agents. This framework is based on a synthetic methodology whose goal is understanding by designing and building. The text includes the background material required to understand the principles underlying intelligence, as well as information of intelligent robotics and simulated agents so readers can begin experiments and projects on their own. The reader is guided through a series of case studies that illustrate the design principles of embodied cognitive science.
(source: Nielsen Book Data)
By the mid-1980s researchers from artificial intelligence, computer science, brain and cognitive science, and psychology realized that the idea of computers as intelligent machines was inappropriate. The brain does not run "programs"; it does something entirely different. But what? Evolutionary theory says that the brain has evolved not to do mathematical proofs but to control our behavior, to ensure our survival. Researchers now agree that intelligence always manifests itself in behavior--thus it is behavior that we must understand. An exciting new field has grown around the study of behavior-based intelligence, also known as embodied cognitive science, "new AI, " and "behavior-based AI."This book provides a systematic introduction to this new way of thinking. After discussing concepts and approaches such as subsumption architecture, Braitenberg vehicles, evolutionary robotics, artificial life, self-organization, and learning, the authors derive a set of principles and a coherent framework for the study of naturally and artificially intelligent systems, or autonomous agents. This framework is based on a synthetic methodology whose goal is understanding by designing and building.The book includes all the background material required to understand the principles underlying intelligence, as well as enough detailed information on intelligent robotics and simulated agents so readers can begin experiments and projects on their own. The reader is guided through a series of case studies that illustrate the design principles of embodied cognitive science.
(source: Nielsen Book Data)

The book provides an overview of recent developments in large margin classifiers, examines connections with other methods (e.g., Bayesian inference), and identifies strengths and weaknesses of the method, as well as directions for future research. The concept of large margins is a unifying principle for the analysis of many different approaches to the classification of data from examples, including boosting, mathematical programming, neural networks, and support vector machines. The fact that it is the margin, or confidence level, of a classification-that is, a scale parameter-rather than a raw training error that matters has become a key tool for dealing with classifiers. This book shows how this idea applies to both the theoretical analysis and the design of algorithms. The book provides an overview of recent developments in large margin classifiers, examines connections with other methods (e.g., Bayesian inference), and identifies strengths and weaknesses of the method, as well as directions for future research. Among the contributors are Manfred Opper, Vladimir Vapnik, and Grace Wahba.
(source: Nielsen Book Data)

The book provides an overview of recent developments in large margin classifiers, examines connections with other methods (e.g., Bayesian inference), and identifies strengths and weaknesses of the method, as well as directions for future research. The concept of large margins is a unifying principle for the analysis of many different approaches to the classification of data from examples, including boosting, mathematical programming, neural networks, and support vector machines. The fact that it is the margin, or confidence level, of a classification-that is, a scale parameter-rather than a raw training error that matters has become a key tool for dealing with classifiers. This book shows how this idea applies to both the theoretical analysis and the design of algorithms. The book provides an overview of recent developments in large margin classifiers, examines connections with other methods (e.g., Bayesian inference), and identifies strengths and weaknesses of the method, as well as directions for future research. Among the contributors are Manfred Opper, Vladimir Vapnik, and Grace Wahba.
(source: Nielsen Book Data)

The book provides an overview of recent developments in large margin classifiers, examines connections with other methods (e.g., Bayesian inference), and identifies strengths and weaknesses of the method, as well as directions for future research. The concept of large margins is a unifying principle for the analysis of many different approaches to the classification of data from examples, including boosting, mathematical programming, neural networks, and support vector machines. The fact that it is the margin, or confidence level, of a classification-that is, a scale parameter-rather than a raw training error that matters has become a key tool for dealing with classifiers. This book shows how this idea applies to both the theoretical analysis and the design of algorithms. The book provides an overview of recent developments in large margin classifiers, examines connections with other methods (e.g., Bayesian inference), and identifies strengths and weaknesses of the method, as well as directions for future research. Among the contributors are Manfred Opper, Vladimir Vapnik, and Grace Wahba.
(source: Nielsen Book Data)

• 1. Dimensions
• 2. Symbolic, conceptual, and subconceptual representations
• 3. Properties
• 4. Concepts
• 5. Semantics
• 6. Induction
• 7. Computational aspects
• 8. In Chase of Space.

Within cognitive science, two approaches currently dominate the problem of modelling representations. The symbolic approach views cognition as computation involving symbolic manipulation. Connectionism, a special case of associationism, models associations using artificial neuron networks. Peter Gardenfors offers his theory of conceptual representations as a bridge between the symbolic and connectionist approaches. Symbolic representation is particularly weak at modeling concept learning, which is paramount for understanding many cognitive phenomena. Concept learning is closely tied to the notion of similarity, which is also poorly served by the symbolic approach. Gardenfors's theory of conceptual spaces presents a framework for representing information on the conceptual level. A conceptual space is built up from geometrical structures based on a number of quality dimensions. The main applications of the theory are on the constructive side of cognitive science: as a constructive model the theory can be applied to the development of artificial systems capable of solving cognitive tasks. Gardenfors also shows how conceptual spaces can serve as an explanatory framework for a number of empirical theories, in particular those concerning concept formation, induction and semantics. His aim is to present a coherent research program that can be used as a basis for more detailed investigations.
(source: Nielsen Book Data)