Machine Learning

1. Front Matter

   Pages i-xi

   PDF

2. General Issues in Machine Learning

   1. Front Matter

      Pages 1-1

      PDF

   2. An Overview of Machine Learning

      • Jaime G. Carbonell, Ryszard S. Michalski, Tom M. Mitchell

      Pages 3-23

   3. Why Should Machines Learn?

      • Herbert A. Simon

      Pages 25-37

3. Learning from Examples

   1. Front Matter

      Pages 39-39

      PDF

   2. A Comparative Review of Selected Methods for Learning from Examples

      • Thomas G. Dietterich, Ryszard S. Michalski

      Pages 41-81

   3. A Theory and Methodology of Inductive Learning

      • Ryszard S. Michalski

      Pages 83-134

4. Learning in Problem-Solving and Planning

   1. Front Matter

      Pages 135-135

      PDF

   2. Learning by Analogy: Formulating and Generalizing Plans from Past Experience

      • Jaime G. Carbonell

      Pages 137-161

   3. Learning by Experimentation: Acquiring and Refining Problem-Solving Heuristics

      • Tom M. Mitchell, Paul E. Utgoff, Ranan Banerji

      Pages 163-190

   4. Acquisition of Proof Skills in Geometry

      • John R. Anderson

      Pages 191-219

   5. Using Proofs and Refutations to Learn from Experience

      • Frederick Hayes-Roth

      Pages 221-240

5. Learning from Observation and Discovery

   1. Front Matter

      Pages 241-241

      PDF

   2. The Role of Heuristics in Learning by Discovery: Three Case Studies

      • Douglas B. Lenat

      Pages 243-306

   3. Rediscovering Chemistry with the Bacon System

      • Pat Langley, Gary L. Bradshaw, Herbert A. Simon

      Pages 307-329

   4. Learning from Observation: Conceptual Clustering

      • Ryszard S. Michalski, Robert E. Stepp

      Pages 331-363

6. Learning from Instruction

   1. Front Matter

      Pages 365-365

      PDF

   2. Machine Transformation of Advice Into a Heuristic Search Procedure

      • David Jack Mostow

      Pages 367-403

   3. Learning By Being Told: Acquiring Knowledge for Information Management

      • Norman Haas, Gary G. Hendrix

      Pages 405-427

   4. The Instructible Production System: A Retrospective Analysis

      • Michael D. Rychener

      Pages 429-459

The ability to learn is one of the most fundamental attributes of intelligent behavior. Consequently, progress in the theory and computer modeling of learn­ ing processes is of great significance to fields concerned with understanding in­ telligence. Such fields include cognitive science, artificial intelligence, infor­ mation science, pattern recognition, psychology, education, epistemology, philosophy, and related disciplines. The recent observance of the silver anniversary of artificial intelligence has been heralded by a surge of interest in machine learning-both in building models of human learning and in understanding how machines might be endowed with the ability to learn. This renewed interest has spawned many new research projects and resulted in an increase in related scientific activities. In the summer of 1980, the First Machine Learning Workshop was held at Carnegie-Mellon University in Pittsburgh. In the same year, three consecutive issues of the Inter­ national Journal of Policy Analysis and Information Systems were specially devoted to machine learning (No. 2, 3 and 4, 1980). In the spring of 1981, a special issue of the SIGART Newsletter No. 76 reviewed current research projects in the field. . This book contains tutorial overviews and research papers representative of contemporary trends in the area of machine learning as viewed from an artificial intelligence perspective. As the first available text on this subject, it is intended to fulfill several needs.

• Lernender Automat
• Mathematische Lerntheorie
• artificial intelligence
• behavior
• cognition
• epistemology
• intelligence
• learning
• machine learning
• modeling
• pattern recognition
• philosophy

• University of Illinois at Urbana-Champaign, USA

  Ryszard S. Michalski

• Carnegie-Mellon University Pittsburgh, USA

  Jaime G. Carbonell

• Rutgers University New Brunswick, USA

  Tom M. Mitchell

Policies and ethics