Foundations of Knowledge Acquisition

1. Front Matter

   Pages i-xi

   PDF

2. Learning = Inferencing + Memorizing

   • Ryszard S. Michalski

   Pages 1-41

3. Adaptive Inference

   • Alberto Segre, Charles Elkan, Daniel Scharstein, Geoffrey Gordon, Alexander Russell

   Pages 43-81

4. On Integrating Machine Learning with Planning

   • Gerald F. DeJong, Melinda T. Gervasio, Scott W. Bennett

   Pages 83-116

5. The Role of Self-Models in Learning to Plan

   • Gregg Collins, Lawrence Birnbaum, Bruce Krulwich, Michael Freed

   Pages 117-143

6. Learning Flexible Concepts Using a Two-Tiered Representation

   • R. S. Michalski, F. Bergadano, S. Matwin, J. Zhang

   Pages 145-202

7. Competition-Based Learning

   • John J. Grefenstette, Kenneth A. De Jong, William M. Spears

   Pages 203-225

8. Problem Solving via Analogical Retrieval and Analogical Search Control

   • Randolph Jones

   Pages 227-262

9. A View of Computational Learning Theory

   • Leslie G. Valiant

   Pages 263-289

10. The Probably Approximately Correct (PAC) and Other Learning Models

    • David Haussler, Manfred Warmuth

    Pages 291-312

11. On the Automated Discovery of Scientific Theories

    • Daniel Osherson, Scott Weinstein

    Pages 313-330

12. Back Matter

    Pages 331-334

    PDF

One of the most intriguing questions about the new computer technology that has appeared over the past few decades is whether we humans will ever be able to make computers learn. As is painfully obvious to even the most casual computer user, most current computers do not. Yet if we could devise learning techniques that enable computers to routinely improve their performance through experience, the impact would be enormous. The result would be an explosion of new computer applications that would suddenly become economically feasible (e. g. , personalized computer assistants that automatically tune themselves to the needs of individual users), and a dramatic improvement in the quality of current computer applications (e. g. , imagine an airline scheduling program that improves its scheduling method based on analyzing past delays). And while the potential economic impact of successful learning methods is sufficient reason to invest in research into machine learning, there is a second significant reason: studying machine learning helps us understand our own human learning abilities and disabilities, leading to the possibility of improved methods in education. While many open questions remain about the methods by which machines and humans might learn, significant progress has been made.

• algorithms
• artificial intelligence
• cognitive science
• genetic algorithms
• intelligence
• learning
• learning theory
• logical reasoning
• machine learning

• Naval Research Laboratory, USA

  Alan L. Meyrowitz

• Office of Naval Research, USA

  Susan Chipman

Policies and ethics