%{search_type} search results

• Introduction: the Turing test in light of the frame problem
• Algorithmic machines and computer learning
• Computer simulation and user illusions
• The Dreyfus critique and the frame problem
• The Turing test, Dennett's defense of the test, and mindlike programs
• The relation of the frame problem to the Turing test
• Two major critiques of the test: Searle and Gunderson
• The frame problem, philosophy, and AI's understanding of intelligence.

Both the Turing test and the frame problem have been significant items of discussion since the 1970s in the philosophy of artificial intelligence (AI) and the philisophy of mind. However, there has been little effort during that time to distill how the frame problem bears on the Turing test. If it proves not to be solvable, then not only will the test not be passed, but it will call into question the assumption of classical AI that intelligence is the manipluation of formal constituens under the control of a program. This text explains why there has been less progress in artificial intelligence research than AI proponents would have believed in the mid-1970s. As a first pass, the difficulty of the frame problem would account for some of the lack of progress. An alternative interpretation is that the research paradigm itself is destined to be less productive than might have been hoped. In general termns, the view advanced here is that the future of AI depends on whether the frame problem eventually falls to computational techniques. If it turns out that the frame problem is computationally irreducible, of there is no way to solve it computationally by means of a program operating on formally defined constituents, then an increasing number of experts in the field will reach the conclusion that AI embodies a fundamental misunderstanding of intelligence.
(source: Nielsen Book Data)

• Mechanisms of mind
• the nature of mind and the mind-body problem
• animal minds
• symbolic AI
• the first AI debate
• connectionism
• the second AI debate
• evolution, natural and artificial
• artificial life
• multiplicity of mind
• what do I do now?
• what's out there?
• remembering and creating
• representation and the third AI debate
• into the future
• an emerging new paradigm of mind?.
• (source: Nielsen Book Data)

Recent decades have produced a blossoming of research in artificial systems that exhibit important properties of mind. But what exactly is this dramatic new work and how does it change the way we think about the mind, or even about who or what has mind?Stan Franklin is the perfect tour guide through the contemporary interdisciplinary matrix of artificial intelligence, cognitive science, cognitive neuroscience, artificial neural networks, artificial life, and robotics that is producing a new paradigm of mind. Leisurely and informal, but always informed, his tour touches on all of the major facets of mechanisms of mind.Along the way, Franklin makes the case for a perspective that rejects a rigid distinction between mind and non-mind in favor of a continuum from less to more mind, and for the role of mind as a control structure with the essential task of choosing the next action. Selected stops include the best of the work in these different fields, with the key concepts and results explained in just enough detail to allow readers to decide for themselves why the work is significant.Major attractions include animal minds, Allan Newell's SOAR, the three Artificial Intelligence debates, John Holland's genetic algorithms, Wilson's Animat, Brooks' subsumption architecture, Jackson's pandemonium theory, Ornstein's multimind, Marvin Minsky's society of mind, Pattie Maes's behavior networks, Gerald Edelman's neural Darwinism, Drescher's schema mechanisms, Pentti Kanerva's sparse distributed memory, Douglas Hofstadter and Melanie Mitchell's Copycat, and Agre and Chapman's deictic representations. A Bradford Book.
(source: Nielsen Book Data)
Recent decades have produced a blossoming of research in artificial systems that exhibit important properties of mind. But what exactly is this dramatic new work and how does it change the way we think about the mind, or even about who or what has mind?
(source: Nielsen Book Data)

• Fuzzy logic and genetic algorithms
• learning
• fuzzy and hybrid systems
• decision and aggregation techniques
• fuzzy logic in databases
• foundations of fuzzy logic
• applications of fuzzy sets.
• (source: Nielsen Book Data)

Soft computing is a new, emerging discipline rooted in a group of technologies that aim to exploit the tolerance for imprecision and uncertainty in achieving solutions to complex problems. The principal components of soft computing are fuzzy logic, neurocomputing, genetic algorithms and probabilistic reasoning.This volume is a collection of up-to-date articles giving a snapshot of the current state of the field. It covers the whole expanse, from theoretical foundations to applications. The contributors are among the world leaders in the field.
(source: Nielsen Book Data)

• 1. Learning, goals, and learning goals / by Ashwin Ram and David B. Leake
• 2. Planning to learn / by Lawrence Hunter
• 3. Quantitative results concerning the utility of explanation-based learning / by Steven Minton
• 4. The use of explicit goals for knowledge to guide inference and learning / by Ashwin Ram and Lawrence Hunter
• 5. Deriving categories to achieve goals / by Lawrence W. Barsalou
• 6. Harpoons and long sticks : the interaction of theory and similarity in rule induction / by Edward J. Wisniewski and Douglas L. Medin
• 7. Introspective reasoning using meta-explanations for multistrategy learning / by Ashwin Ram and Michael T. Cox
• 8. Goal-directed learning : a decision-theoretic model for deciding what to learn next / by Marie desJardins
• 9. Goal-based explanation evaluation / by David B. Leake
• 10. Planning to perceive / by Louise Pryor and Gregg Collins
• 11. Planning and learning in PRODIGY : overview of an integrated architecture / by Jaime Carboneil [and others]
• 12. A learning model for the selection of problem-solving strategies in continuous physical systems / by Xiaodong Xia and Dif-Yan Yeung
• 13. Explicitly biased generalization / by Diana Gordon and Donald Perlis
• 14. Three levels of goal orientation in learning / by Evelyn Ng and Carl Bereiter
• 15. Characterizing the application of computer simulations in education : instructional criteria / by Jos J.A. van Berkum [and others]
• 16. Goal-driven learning : fundamental issues and symposium report / by David B. Leake and Ashwin Ram
• 17. Storage side effects : studying processing to understand learning / by Lawrence W. Barsalou
• 18. Goal-driven learning in multistrategy reasoning and learning systems / by Ashwin Ram, Michael T. Cox and S. Narayanan
• 19. Inference to the best plan : a coherence theory of decision / by Paul Thagard and Elija Millgram
• 20. Toward goal-driven integration of explanation and action / by David B. Leake
• 21. Learning as goal-driven inference / by Ryszard Michalski and Ashwin Ram.

In cognitive science, artificial intelligence, psychology, and education, a growing body of research supports the view that the learning process is strongly influenced by the learner's goals. The fundamental tenet of goal-driven learning is that learning is largely an active and strategic process in which the learner, human or machine, attempts to identify and satisfy its information needs in the context of its tasks and goals, its prior knowledge, its capabilities, and environmental opportunities for learning. This book brings together a diversity of research on goal-driven learning to establish a broad, interdisciplinary framework that describes the goal-driven learning process. It collects and solidifies existing results on this important issue in machine and human learning and presents a theoretical framework for future investigations. The book opens with an an overview of goal-driven learning research and computational and cognitive models of the goal-driven learning process. This introduction is followed by a collection of fourteen recent research articles addressing fundamental issues of the field, including psychological and functional arguments for modeling learning as a deliberative, planful process; experimental evaluation of the benefits of utility-based analysis to guide decisions about what to learn; case studies of computational models in which learning is driven by reasoning about learning goals; psychological evidence for human goal-driven learning; and the ramifications of goal-driven learning in educational contexts. The second part of the book presents six position papers reflecting ongoing research and current issues in goal-driven learning. Issues discussed include methods for pursuing psychological studies of goal-driven learning, frameworks for the design of active and multistrategy learning systems, and methods for selecting and balancing the goals that drive learning. A Bradford Book.
(source: Nielsen Book Data)
In cognitive science, artificial intelligence, psychology, and education, a growing body of research supports the view that the learning process is strongly influenced by the learner's goals. The fundamental tenet of goal-driven learning is that learning is largely an active and strategic process in which the learner, human or machine, attempts to identify and satisfy its information needs in the context of its tasks and goals, its prior knowledge, its capabilities, and environmental opportunities for learning. This book brings together a diversity of research on goal-driven learning to establish a broad, interdisciplinary framework that describes the goal-driven learning process. It collects and solidifies existing results on this important issue in machine and human learning and presents a theoretical framework for future investigations.
(source: Nielsen Book Data)

Within artificial intelligence, the need to create sophisticated, intelligent behaviour based on common-sense reasoning has long been recognized. Research has demonstrated that formalism for dealing with common sense reasoning require nonmonotonic capabilities where, typically, inferences based on incomplete knowledge need to be revised in light of later information which fills in some of the gaps.
(source: Nielsen Book Data)

• The Road to Intelligent Machines
• The Power and Limitations of Perceptrons
• Neural Logic Networks
• Probabilistic Neural Logic Networks
• Fuzzy Neural Logic Networks
• Temporal Neural Logic Networks
• Neural Logic Programming
• Connectionist Expert Systems
• Fuzzy Knowledge Processing
• The Art of Guessing.
• (source: Nielsen Book Data)

This book is the first of a series of technical reports of a key research project of the Real-World Computing Program supported by the MITI of Japan.The main goal of the project is to model human intelligence by a special class of mathematical systems called neural logic networks.The book consists of three parts. Part 1 describes the general theory of neural logic networks and their potential applications. Part 2 discusses a new logic called Neural Logic which attempts to emulate more closely the logical thinking process of human. Part 3 studies the special features of neural logic networks which resemble the human intuition process.This book should appeal to researchers in artificial intelligence, neural computings and logic, as well as graduate and advance undergraduate students in computer science.
(source: Nielsen Book Data)

• From recognition to analogy-making - the central role of slippage
• the Tabletop microdomain
• the architecture of Tabletop
• Tabletop's performance up close
• Tabletop's personality profile
• comparisons with other work
• summary and conclusions.
• (source: Nielsen Book Data)

Foreword by Daniel Dennett While it is fashionable today to dismiss the "bad old days" of artificial intelligence and rave about emergent self-organizing systems, Robert French has created a model of human analogy-making that attempts to bridge the gap between classical top-down AI and more recent bottom-up approaches.
(source: Nielsen Book Data)
The research described in this book is based on the premise that human analogy-making is an extension of our constant background process of perceiving-in other words, that analogy-making and the perception of sameness are two sides of the same coin. Foreword by Daniel Dennett While it is fashionable today to dismiss the "bad old days" of artificial intelligence and rave about emergent self-organizing systems, Robert French has created a model of human analogy-making that attempts to bridge the gap between classical top-down AI and more recent bottom-up approaches. The research described in this book is based on the premise that human analogy-making is an extension of our constant background process of perceiving-in other words, that analogy-making and the perception of sameness are two sides of the same coin. At the heart of the author's theory and computer model of analogy-making is the idea that the building-up and the manipulation of representations are inseparable aspects of mental functioning, in contrast to traditional AI models of high-level cognitive processes, which have almost always depended on a clean separation. A computer program called Tabletop forms analogies in a microdomain consisting of everyday objects on a table set for a meal. The theory and the program rely on the idea that myriad stochastic choices made on the microlevel can add up to statistical robustness on a macrolevel. To illustrate this, French includes the results of thousands of runs of his program on several dozen interrelated analogy problems in the Tabletop microworld. French's work is exciting not only because it reveals analogy-making to be an extension of our complex and subtle ability to perceive sameness but also because it offers a computational model of mechanisms underlying these processes. This model makes significant strides in putting into practice microlevel stochastic processing, distributed processing, simulated parallelism, and the integration of representation-building and representation-processing. A Bradford Book.
(source: Nielsen Book Data)

• Neural network performance metrics
• noise in neural implementations
• simulation requirements and environment
• fault tolerance
• generalisation ability
• learning trajectory and speed.
• (source: Nielsen Book Data)

Hardware inaccuracy and imprecision are important considerations when implementing neural algorithms. This book presents a study of synaptic weight noise as a typical fault model for analogue VLSI realisations of MLP neural networks and examines the implications for learning and network performance. The aim of the book is to present a study of how including an imprecision model into a learning scheme as a"fault tolerance hint" can aid understanding of accuracy and precision requirements for a particular implementation. In addition the study shows how such a scheme can give rise to significant performance enhancement.
(source: Nielsen Book Data)

Machine learning is a relatively new branch of artificial intelligence. The field has undergone a significant period of growth in the 1990s, with many new areas of research and development being explored.
(source: Nielsen Book Data)

• PART I: A COMPARISON OF EVOLUTIONARY ALGORITHMS
• PART II: EXTENDING GENETIC ALGORITHMS.
• (source: Nielsen Book Data)

PART I: Comparison of Evolutionary Algorithms. 1. Organic Evolution and Problem Solving. 2. Specific Evolutionary Algorithms. 3. Artificial Landscapes. 4. An Empirical Comparison. PART II: Extending Genetic Algorithms. 5. Selection. 6. Mutation. 7. An Experiment in Meta-Evolution.
(source: Nielsen Book Data)
This book compares the three most prominent representatives of evolutionary algorithms - genetic algorithms, evolution strategies, and evolutionary programming - computational methods at the border between computer science and evolutionary biology. The algorithms are explained within a common formal framework, thereby clarifying the similarities and differences of these methods. The author also presents new results regarding the role of mutation and selection in genetic algorithms and uses a meta-evolutionary approach to confirm some of the theoretical results.
(source: Nielsen Book Data)

• 1. The faculty of knowledge engineering and problem solving
• 2. Knowledge engineering and symbolic artificial intelligence
• 3. From fuzzy sets to fuzzy systems
• 4. Neural networks : theoretical and computational models
• 5. Neural networks for knowledge engineering and problem solving
• 6. Hybrid symbolic, fuzzy, and connectionist systems : toward comprehensive artificial intelligence
• 7. Neural networks, fuzzy systems, and nonlinear dynamical systems. chaos ; toward new connectionist and fuzzy logic models.

"Covering the latest issues and achievements, this well documented, precisely presented text is timely and suitable for graduate and upper undergraduate students in knowledge engineering, intelligent systems, AI, neural networks, fuzzy systems, and related areas. The author's goal is to explain the principles of neural networks and fuzzy systems and to demonstrate how they can be applied to building knowledge-based systems for problem solving. Especially useful are the comparisons between different techniques (AI rule-based methods, fuzzy methods, connectionist methods, hybrid systems) used to solve the same or similar problems.".
(source: Nielsen Book Data)
Neural networks and fuzzy systems are different aprpoaches to introducing human-like reasoning into expert systems. This text combines the study of these two subjects, their basics and their use, along with symbolic AI methods to build comprehensive artificial intelligence systems. Kasabov describes rule-based and connectionist techniques and then their combinations, with fuzzy logic included, showing the application of the different techniques to a set of simple prototype problems, which makes comparisons possible. A particular feature of the text is that it is filled with applications in engineering, business and finance. AI problems that cover most of the application-oriented research in the field (pattern recognition, speech and image processing, classification, planning, optimization, prediction, control, decision making, and game simulations) are discussed and illustrated with concrete examples. Intended both as a text for advanced undergraduate and postgraduate students as well as a reference for researchers in the field of knowledge engineering, "Foundations of Neural Networks, Fuzzy Systems and Knowledge Engineering" has chapters structured for various levels of teaching and includes work by the author along with the classic material. Data sets for the examples in the book as well as an integrated software environment that can be used to solve the problems and do the exercises at the end of each chapter are available free through anonymous ftp.
(source: Nielsen Book Data)

• Hardware and software aspects
• transputer topologies for parallel implementation
• comparison between serial and parallel implementation
• analysis and implementation for equal distribution of the training set in a homogeneous transputer array
• analysis and implementation for unequal distribution of the training set in a homogeneous transputer array
• analysis and implementation for unequal distribution of the training set in a heterogeneous transputer array
• conclusion.
• (source: Nielsen Book Data)

This book presents a systematic approach to parallel implementation of feedforward neural networks on an array of transputers. The emphasis is on backpropagation learning and training set parallelism. Using systematic analysis, a theoretical model has been developed for the parallel implementation. The model is used to find the optimal mapping to minimize the training time for large backpropagation neural networks. The model has been validated experimentally on several well known benchmark problems. Use of genetic algorithms for optimizing the performance of the parallel implementations is described. Guidelines for efficient parallel implementations are highlighted.
(source: Nielsen Book Data)

• Fuzzy compensation principles
• normal fuzzy reasoning methodology
• compensatory genetic fuzzy neural networks
• fuzzy knowledge rediscovery in fuzzy rule bases
• fuzzy cat-pole balancing control systems
• fuzzy knowledge compression and expansion
• highly nonlinear system modelling and prediction
• fuzzy moves in fuzzy games
• genetic neuro-fuzzy pattern recognition
• constructive approach to modelling fuzzy systems.
• (source: Nielsen Book Data)

This book presents a powerful hybrid intelligent system based on fuzzy logic, neural networks, genetic algorithms and related intelligent techniques. The new compensatory genetic fuzzy neural networks have been widely used in fuzzy control, nonlinear system modeling, compression of a fuzzy rule base, expansion of a sparse fuzzy rule base, fuzzy knowledge discovery, time series prediction, fuzzy games and pattern recognition. This effective soft computing system is able to perform both linguistic-word-level fuzzy reasoning and numerical-data-level information processing. The book also proposes various novel soft computing techniques.
(source: Nielsen Book Data)

• Helicopter flight control with fuzzy logic and genetic algorithms, C. Philips et al
• skill acquisition and skill-based motion planning for hierarchical intelligent control of a redundant manipulator, T. Shibata
• a creative design of fuzzy logic controller using a genetic algorithm, T. Hashiyama et al
• automatic fuzzy tuning and its applications, H. Ishigami et al
• an evolutionary algorithm for fuzzy controller synthesis and optimization based on SGS-Thomson's W.A.R.P. fuzzy processor, R. Poluzzi et al
• on-line self-structuring fuzzy inference systems for function approximation, H. Bersini
• fuzzy classification based on adaptive networks and genetic algorithms, C.-T. Sun and J.-S. Jang
• intelligent systems for fraud detection, J. Kingdon
• genetic algorithms for query optimization in information retrieval - relevance feedback, D.H. Kraft et al
• fuzzy fitness assignment in an interactive genetic algorithm for a cartoon face search, K. Nishio et al
• an evolutionary approach to simulate cognitive feedback learning in medical domain, H.S. Lopes et al
• a classified review on the combination fuzzy logic-genetic algorithms bibliography - 1989-1995, O. Cordon et al.
• (source: Nielsen Book Data)

Ever since fuzzy logic was introduced by Lotfi Zadeh in the mid-sixties and genetic algorithms by John Holland in the early seventies, these two fields widely been subjects of academic research the world over. During the last few years, they have been experiencing extremely rapid growth in the industrial world, where they have been shown to be very effective in solving real-world problems. These two substantial fields, together with neurocomputing techniques, are recognized as major parts of soft computing: a set of computing technologies already riding the waves of the next century to produce the human-centered intelligent systems of tomorrow; the collection of papers presented in this book shows the way. The book also contains an extensive bibliography on fuzzy logic and genetic algorithms.
(source: Nielsen Book Data)

• A new way to acquire knowledge, H.-Y. Wang
• an SPN knowledge representation scheme, J. Gattiker and N. Bourbakis
• on the deep structures of word problems and their construction, F. Gomez
• resolving conflicts in inheritance reasoning with statistical approach, C. Lee
• integrating high and low level computer vision for scene understanding, R. Malik and S. So
• the evolution of commercial AI tools - the first decade, F. Hayes-Roth
• reengineering - the AT generation - billions on the table, J.S. Minor, Jr.
• an intelligent tool for discovering data dependencies in relational DBS, P. Gavaskar and F. Golshani
• a case-based reasoning (CBR) tool to assist traffic flow, B. Das and S. Bayles
• a study of financial expert system based on flops, T. Kaneko and K. Takenaka
• an associative data parallel compilation model for tight integration of high performance knowledge retrieval and computation, A. Bansal
• software automation - from silly to intelligent, X. Jiafu et al
• software engineering using artificial intelligence - the knowledge based software assistant, D. White
• knowledge based derivation of programmes from specs, T. Weight et al
• automatic functional model generation for parallel fault design error simulations, S.E. Chang and S. Szygenda
• visual reverse engineering using SPN for automated diagnosis and functional simulation of digital circuits, J. Gattiker and S. Mertoguno
• the impact of AI in VLSI design automation, M. Mortazavi and N. Bourbakis
• the automated acquisition of subcategorization of verbs, nouns and adjectives from sample sentences, F. Gomez
• general method for planning and rendezvous problems, K. Trovato
• learning to improve path planning performance, P.C. Chen
• incremental adaptation as a method to improve reactive behaviour, A.J. Hendriks and D.M. Lyons
• an SPN-neural planning methodology for coordination of multiple robotic arms with constrained placement, N. Bourbakis and A. Tascillo.
• (source: Nielsen Book Data)

Covering artificial intelligence and automation, these contributions discuss: the evolution of AI tools; an SPN knowledge representation scheme; software engineering using AI; the impact of AI in VLSI design automation; incremental adaptation as a method to improve reactive behaviour; and more.
(source: Nielsen Book Data)

• Approximate reasoning about comlpex objects in distributed systems - rough mereological formulation
• FOOD - fuzzy object-oriented design
• approximating block access in database systems
• the computer zoo in a box
• expert system design
• automating creation of computer programs for design circuits using genetic programming
• self-organizing maps
• knowledge-based techniques for software quality management
• object networks in developing intelligent systems
• application of genetic programming in software quality prediction
• neural networks for software quality prediction
• fuzzy Petri nets and Choquet integral in software cost estimation
• non-Cartesian approach to software development
• inductive programming.
• (source: Nielsen Book Data)

This unique volume is the first publication on software engineering and computational intelligence (CI) viewed as a synergistic interplay of neurocomputing, granular computation (including fuzzy sets and rough sets), and evolutionary methods. It presents a unified view of CI in the context of software engineering.The book addresses a number of crucial issues: what is CI, what role does it play in software development, how are CI elements built into successive phases of the software life cycle, and what is the role played by CI in quantifying fundamental features of software artifacts?With contributions from leading researchers and practitioners, the book provides the reader with a wealth of new concepts and approaches, complete algorithms, in-depth case studies, and thought-provoking exercises. The topics coverage include neurocomputing, granular as well as evolutionary computing, object-oriented analysis and design in software engineering. There is also an extensive bibliography.
(source: Nielsen Book Data)

• 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 new algorithms. Among the algorithms described are the wake-sleep algorithm for unsupervised learning, the iterative turbodecoding algorithm (currently the best error-correcting decoding 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)

• 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)