Based on a symposium honoring the extensive work of Allen Newell -- one of the founders of artificial intelligence, cognitive science, human-computer interaction, and the systematic study of computational architectures -- this volume demonstrates how unifying themes may be found in the diversity that characterizes current research on computers and cognition. The subject matter includes:
* an overview of cognitive and computer science by leading researchers in the field;
* a comprehensive description of Allen Newell's "Soar" -- a computational architecture he developed as a unified theory of cognition;
* commentary on how the Soar theory of cognition relates to important issues in cognitive and computer science;
* rigorous treatments of controversial issues in cognition -- methodology of cognitive science, hybrid approaches to machine learning, word-sense disambiguation in understanding material language, and the role of capability processing constraints in architectural theory;
* comprehensive and systematic methods for studying architectural evolution in both hardware and software;
* a thorough discussion of the use of analytic models in human computer interaction;
* extensive reviews of important experiments in the study of scientific discovery and deduction; and
* an updated analysis of the role of symbols in information processing by Herbert Simon.
Incorporating the research of top scientists inspired by Newell's work, this volume will be of strong interest to a large variety of scientific communities including psychologists, computational linguists, computer scientists and engineers, and interface designers. It will also be valuable to those who study the scientific process itself, as it chronicles the impact of Newell's approach to research, simultaneously delving into each scientific discipline and producing results that transcend the boundaries of those disciplines.

Based on a symposium honoring the extensive work of Allen Newell -- one of the founders of artificial intelligence, cognitive science, human-computer interaction, and the systematic study of computational architectures -- this volume demonstrates how unifying themes may be found in the diversity that characterizes current research on computers and cognition. The subject matter includes:
* an overview of cognitive and computer science by leading researchers in the field;
* a comprehensive description of Allen Newell's "Soar" -- a computational architecture he developed as a unified theory of cognition;
* commentary on how the Soar theory of cognition relates to important issues in cognitive and computer science;
* rigorous treatments of controversial issues in cognition -- methodology of cognitive science, hybrid approaches to machine learning, word-sense disambiguation in understanding material language, and the role of capability processing constraints in architectural theory;
* comprehensive and systematic methods for studying architectural evolution in both hardware and software;
* a thorough discussion of the use of analytic models in human computer interaction;
* extensive reviews of important experiments in the study of scientific discovery and deduction; and
* an updated analysis of the role of symbols in information processing by Herbert Simon.
Incorporating the research of top scientists inspired by Newell's work, this volume will be of strong interest to a large variety of scientific communities including psychologists, computational linguists, computer scientists and engineers, and interface designers. It will also be valuable to those who study the scientific process itself, as it chronicles the impact of Newell's approach to research, simultaneously delving into each scientific discipline and producing results that transcend the boundaries of those disciplines.

Recent Advances in Robot Learning contains seven papers on robot learning written by leading researchers in the field. As the selection of papers illustrates, the field of robot learning is both active and diverse. A variety of machine learning methods, ranging from inductive logic programming to reinforcement learning, is being applied to many subproblems in robot perception and control, often with objectives as diverse as parameter calibration and concept formulation. While no unified robot learning framework has yet emerged to cover the variety of problems and approaches described in these papers and other publications, a clear set of shared issues underlies many robot learning problems. Machine learning, when applied to robotics, is situated: it is embedded into a real-world system that tightly integrates perception, decision making and execution. Since robot learning involves decision making, there is an inherent active learning issue. Robotic domains are usually complex, yet the expense of using actual robotic hardware often prohibits the collection of large amounts of training data. Most robotic systems are real-time systems. Decisions must be made within critical or practical time constraints. These characteristics present challenges and constraints to the learning system. Since these characteristics are shared by other important real-world application domains, robotics is a highly attractive area for research on machine learning. On the other hand, machine learning is also highly attractive to robotics. There is a great variety of open problems in robotics that defy a static, hand-coded solution. Recent Advances in Robot Learning is an edited volume of peer-reviewed original research comprising seven invited contributions by leading researchers. This research work has also been published as a special issue of Machine Learning (Volume 23, Numbers 2 and 3).

One of the currently most active research areas within Artificial Intelligence is the field of Machine Learning. which involves the study and development of computational models of learning processes. A major goal of research in this field is to build computers capable of improving their performance with practice and of acquiring knowledge on their own. The intent of this book is to provide a snapshot of this field through a broad. representative set of easily assimilated short papers. As such. this book is intended to complement the two volumes of Machine Learning: An Artificial Intelligence Approach (Morgan-Kaufman Publishers). which provide a smaller number of in-depth research papers. Each of the 77 papers in the present book summarizes a current research effort. and provides references to longer expositions appearing elsewhere. These papers cover a broad range of topics. including research on analogy. conceptual clustering. explanation-based generalization. incremental learning. inductive inference. learning apprentice systems. machine discovery. theoretical models of learning. and applications of machine learning methods. A subject index IS provided to assist in locating research related to specific topics. The majority of these papers were collected from the participants at the Third International Machine Learning Workshop. held June 24-26. 1985 at Skytop Lodge. Skytop. Pennsylvania. While the list of research projects covered is not exhaustive. we believe that it provides a representative sampling of the best ongoing work in the field. and a unique perspective on where the field is and where it is headed.

Recent Advances in Robot Learning contains seven papers on robot learning written by leading researchers in the field. As the selection of papers illustrates, the field of robot learning is both active and diverse. A variety of machine learning methods, ranging from inductive logic programming to reinforcement learning, is being applied to many subproblems in robot perception and control, often with objectives as diverse as parameter calibration and concept formulation. While no unified robot learning framework has yet emerged to cover the variety of problems and approaches described in these papers and other publications, a clear set of shared issues underlies many robot learning problems. Machine learning, when applied to robotics, is situated: it is embedded into a real-world system that tightly integrates perception, decision making and execution. Since robot learning involves decision making, there is an inherent active learning issue. Robotic domains are usually complex, yet the expense of using actual robotic hardware often prohibits the collection of large amounts of training data. Most robotic systems are real-time systems. Decisions must be made within critical or practical time constraints. These characteristics present challenges and constraints to the learning system. Since these characteristics are shared by other important real-world application domains, robotics is a highly attractive area for research on machine learning. On the other hand, machine learning is also highly attractive to robotics. There is a great variety of open problems in robotics that defy a static, hand-coded solution. Recent Advances in Robot Learning is an edited volume of peer-reviewed original research comprising seven invited contributions by leading researchers. This research work has also been published as a special issue of Machine Learning (Volume 23, Numbers 2 and 3).

One of the currently most active research areas within Artificial Intelligence is the field of Machine Learning. which involves the study and development of computational models of learning processes. A major goal of research in this field is to build computers capable of improving their performance with practice and of acquiring knowledge on their own. The intent of this book is to provide a snapshot of this field through a broad. representative set of easily assimilated short papers. As such. this book is intended to complement the two volumes of Machine Learning: An Artificial Intelligence Approach (Morgan-Kaufman Publishers). which provide a smaller number of in-depth research papers. Each of the 77 papers in the present book summarizes a current research effort. and provides references to longer expositions appearing elsewhere. These papers cover a broad range of topics. including research on analogy. conceptual clustering. explanation-based generalization. incremental learning. inductive inference. learning apprentice systems. machine discovery. theoretical models of learning. and applications of machine learning methods. A subject index IS provided to assist in locating research related to specific topics. The majority of these papers were collected from the participants at the Third International Machine Learning Workshop. held June 24-26. 1985 at Skytop Lodge. Skytop. Pennsylvania. While the list of research projects covered is not exhaustive. we believe that it provides a representative sampling of the best ongoing work in the field. and a unique perspective on where the field is and where it is headed.

Machine Learning: An Artificial Intelligence Approach contains tutorial overviews and research papers representative of trends in the area of machine learning as viewed from an artificial intelligence perspective. The book is organized into six parts. Part I provides an overview of machine learning and explains why machines should learn. Part II covers important issues affecting the design of learning programs-particularly programs that learn from examples. It also describes inductive learning systems. Part III deals with learning by analogy, by experimentation, and from experience. Parts IV and V discuss learning from observation and discovery, and learning from instruction, respectively. Part VI presents two studies on applied learning systems-one on the recovery of valuable information via inductive inference; the other on inducing models of simple algebraic skills from observed student performance in the context of the Leeds Modeling System (LMS). This book is intended for researchers in artificial intelligence, computer science, and cognitive psychology; students in artificial intelligence and related disciplines; and a diverse range of readers, including computer scientists, robotics experts, knowledge engineers, educators, philosophers, data analysts, psychologists, and electronic engineers.