Skip to main content
Elsevier

Morgan Kaufmann

  • Computing Perspectives

    • 1st Edition
    • Maurice V. Wilkes
    • English
    In this insightful collection of essays, Maurice Wilkes shares his unique perspective on the development of computers and the current state of the art. These enlightening essays discuss the foundational ideas behind modern computing and provide a solid grounding for the appreciation of emerging computer technologies.Wilkes, one of the founders of computing, has provided enormous contributions to the development of computers, including the design and construction of the EDSAC computer and early development of programming for a stored program computer. He was responsible for the concept of microprogramming. Wilkes also wrote the first paper to appear on cache memories and was an early worker in the field of wide bandwidth local area networks. In 1992 he was awarded the prestigious Kyoto Prize for Advanced Technology.These essays will be of interest to everyone involved with computers and how they arrived at their present state. Wilkes presents his perspectives with keen historical sensibility and engineering practicality. Readers are invited to consider these observations and form their own perspectives on the present state of the computer art.

  • Machine Learning Proceedings 1989

    • 1st Edition
    • Alberto Maria Segre
    • English
    Proceedings of the Sixth International Workshop on Machine Learning covers the papers presented at the Sixth International Workshop of Machine Learning, held at Cornell University, Ithaca, New York (USA) on June 26-27, 1989. The book focuses on the processes, methodologies, techniques, and approaches involved in machine learning. The selection first offers information on unifying themes in empirical and explanation-based learning; integrated learning of concepts with both explainable and conventional aspects; conceptual clustering of explanations; and tight integration of deductive and inductive learning. The text then examines multi-strategy learning in nonhomogeneous domain theories; description of preference criterion in constructive learning; and combining case-based reasoning, explanation-based learning, and learning from instruction. Discussions focus on causal explanation of actions, constructive learning, learning in a weak theory domain, learning problem, and individual criteria and their relationships. The book elaborates on learning from plausible explanations, augmenting domain theory for explanation-based generalization, reducing search and learning goal preferences, and using domain knowledge to improve inductive learning algorithms for diagnosis. The selection is a dependable reference for researchers interested in the dynamics of machine learning.

  • Readings in Computer Vision

    Issues, Problem, Principles, and Paradigms
    • 1st Edition
    • Martin A. Fischler + 1 more
    • English
    The field of computer vision combines techniques from physics, mathematics, psychology, artificial intelligence, and computer science to examine how machines might construct meaningful descriptions of their surrounding environment. The editors of this volume, prominent researchers and leaders of the SRI International AI Center Perception Group, have selected sixty papers, most published since 1980, with the viewpoint that computer vision is concerned with solving seven basic problems:Reconstruct... 3D scenes from 2D imagesDecomposing images into their component partsRecognizing and assigning labels to scene objectsDeducing and describing relations among scene objectsDetermining the nature of computer architectures that can support the visual functionRepresenting abstractions in the world of computer memoryMatching stored descriptions to image representationEach chapter of this volume addresses one of these problems through an introductory discussion, which identifies major ideas and summarizes approaches, and through reprints of key research papers. Two appendices on crucial assumptions in image interpretation and on parallel architectures for vision applications, a glossary of technical terms, and a comprehensive bibliography and index complete the volume.

  • COLT '89

    Proceedings of the Second Annual Workshop, UC Santa Cruz, California, July 31 - August 2 1989
    • 1st Edition
    • COLT
    • English
    Computational Learning Theory presents the theoretical issues in machine learning and computational models of learning. This book covers a wide range of problems in concept learning, inductive inference, and pattern recognition. Organized into three parts encompassing 32 chapters, this book begins with an overview of the inductive principle based on weak convergence of probability measures. This text then examines the framework for constructing learning algorithms. Other chapters consider the formal theory of learning, which is learning in the sense of improving computational efficiency as opposed to concept learning. This book discusses as well the informed parsimonious (IP) inference that generalizes the compatibility and weighted parsimony techniques, which are most commonly applied in biology. The final chapter deals with the construction of prediction algorithms in a situation in which a learner faces a sequence of trials, with a prediction to be given in each and the goal of the learner is to make some mistakes. This book is a valuable resource for students and teachers.

  • Machine Learning Proceedings 1992

    Proceedings of the Ninth International Workshop (ML92)
    • 1st Edition
    • Peter Edwards + 1 more
    • English
    Machine Learning: Proceedings of the Ninth International Workshop (ML92) covers the papers and posters presented at ML92, the Ninth International Machine Learning Conference, held at Aberdeen, Scotland on July 1-3, 1992. The book focuses on the advancements of practices, methodologies, approaches, and techniques in machine learning. The selection first offers information on the principal axes method for constructive induction; learning by incomplete explanations of failures in recursive domains; and eliminating redundancy in explanation-based learning. Topics include means-ends analysis search in recursive domains, description space transformation, distance metric, generating similarity matrix, and learning principal axes. The text then examines trading off consistency and efficiency in version-space induction; improving path planning with learning; finding the conservation of momentum; and learning to predict in uncertain continuous tasks. The manuscript elaborates on a teaching method for reinforcement learning, compiling prior knowledge into an explicit bias, spatial analogy and subsumption, and multistrategy learning with introspective meta-explanations. The publication also ponders on selecting typical instances in instance-based learning and temporal difference learning of backgammon strategy. The selection is a valuable source of information for researchers interested in machine learning.

  • Uncertainty in Artificial Intelligence

    Proceedings of the Tenth Conference on Uncertainty in Artificial Intelligence, University of Washington, Seattle, July 29-31, 1994
    • 1st Edition
    • MKP
    • English
    Uncertainty in Artificial Intelligence: Proceedings of the Tenth Conference (1994) covers the papers accepted for presentation at the Tenth Annual Conference on Uncertainty in Artificial Intelligence, held in Seattle, Washington on July 29-31, 1994. The book focuses on the processes, methodologies, and approaches involved in artificial intelligence, including approximations, computational methods, Bayesian networks, and probabilistic inference. The selection first offers information on ending-based strategies for part-of-speech tagging; an evaluation of an algorithm for inductive learning of Bayesian belief networks using simulated data sets; and probabilistic constraint satisfaction with non-Gaussian noise. The text then examines Laplace's method approximations for probabilistic inference in belief networks with continuous variables; computational methods, bounds, and applications of counterfactual probabilities; and approximation algorithms for the loop cutset problem. The book takes a look at learning in multi-level stochastic games with delayed information; properties of Bayesian belief network learning algorithms; and the relation between kappa calculus and probabilistic reasoning. The manuscript also elaborates on intercausal independence and heterogeneous factorization; evidential reasoning with conditional belief functions; and state-space abstraction for anytime evaluation of probabilistic networks. The selection is a valuable reference for researches interested in artificial intelligence.

  • Machine Learning Proceedings 1994

    Proceedings of the Eighth International Conference
    • 1st Edition
    • William W. Cohen
    • English
    Machine Learning: Proceedings of the Eleventh International Conference covers the papers presented at the Eleventh International Conference on Machine Learning (ML94), held at New Brunswick, New Jersey on July 10-13, 1994. The book focuses on the processes, methodologies, and approaches involved in machine learning, including inductive logic programming, neural networks, and decision trees. The selection first offers information on learning recursive relations with randomly selected small training sets; improving accuracy of incorrect domain theories; and using sampling and queries to extract rules from trained neural networks. The text then takes a look at boosting and other machine learning algorithms; an incremental learning approach for completable planning; and learning disjunctive concepts by means of genetic algorithms. The publication ponders on rule induction for semantic query optimization; irrelevant features and the subset selection problem; and an efficient subsumption algorithm for inductive logic programming. The book also examines Bayesian inductive logic programming; a statistical approach to decision tree modeling; and an improved algorithm for incremental induction of decision trees. The selection is a dependable source of data for researchers interested in machine learning.

  • Scalable Shared-Memory Multiprocessing

    • 1st Edition
    • Daniel E. Lenoski + 1 more
    • English
    Dr. Lenoski and Dr. Weber have experience with leading-edge research and practical issues involved in implementing large-scale parallel systems. They were key contributors to the architecture and design of the DASH multiprocessor. Currently, they are involved with commercializing scalable shared-memory technology.

  • Reasoning About Plans

    • 1st Edition
    • James Allen + 3 more
    • English
    This book presents four contributions to planning research within an integrated framework. James Allen offers a survey of his research in the field of temporal reasoning, and then describes a planning system formalized and implemented directly as an inference process in the temporal logic. Starting from the same logic, Henry Kautz develops the first formal specification of the plan recognition process and develops a powerful family of algorithms for plan recognition in complex situations. Richard Pelavin then extends the temporal logic with model operators that allow the representation to support reasoning about complex planning situations involving simultaneous interacting actions, and interaction with external events. Finally, Josh Tenenberg introduces two different formalisms of abstraction in planning systems and explores the properties of these abstraction techniques in depth.

  • Machine Learning Proceedings 1995

    Proceedings of the Twelfth International Conference on Machine Learning, Tahoe City, California, July 9-12 1995
    • 1st Edition
    • Armand Prieditis + 1 more
    • English
    Machine Learning: Proceedings of the Twelfth International Conference on Machine Learning covers the papers presented at the Twelfth International Conference on Machine Learning (ML95), held at the Granlibakken Resort in Tahoe City, California on July 9-12, 1995. The book focuses on the processes, methodologies, principles, and approaches involved in machine learning, including inductive logic programming algorithms, neural networks, and decision trees. The selection first offers information on the theory and applications of agnostic PAC-learning with small decision trees; reinforcement learning with function approximation; and inductive learning of reactive action models. Discussions focus on inductive logic programming algorithm, collecting instances for learning, residual gradient algorithms, direct algorithms, and learning curves for decision trees of small depth. The text then elaborates on visualizing high-dimensional structure with the incremental grid growing neural network; empirical support for winnow and weighted-majority based algorithms; and automatic selection of split criterion during tree growing based on node location. The manuscript takes a look at learning hierarchies from ambiguous natural language data, learning with rare cases and small disjuncts, learning by observation and practice, and learning collection fusion strategies for information retrieval. The selection is a valuable source of data for mathematicians and researchers interested in machine learning.

Browse by Publisher