Machine Learning, Meta-Reasoning and Logics

1. Front Matter

   Pages i-xx

   PDF

2. Meta-Reasoning and Machine Learning

   1. Front Matter

      Pages 1-1

      PDF

   2. A Metalevel Manifesto

      • D. Paul Benjamin

      Pages 3-17

   3. A Sketch of Autonomous Learning using Declarative Bias

      • Stuart J. Russell, Benjamin N. Grosof

      Pages 19-53

   4. Shift of Bias as Non-Monotonic Reasoning

      • Benjamin N. Grosof, Stuart J. Russell

      Pages 55-83

   5. Mutual Constraints on Representation and Inference

      • Stuart Russell, Devika Subramanian

      Pages 85-106

   6. Meta-Reasoning: Transcription of an Invited Lecture by

      • Luigia Aiello

      Pages 107-112

3. Back Matter

   Pages 113-118

   PDF

4. Reasoning about Proofs and Explanations

   1. Front Matter

      Pages 119-119

      PDF

   2. Overgenerality in Explanation-Based Generalization

      • Haym Hirsh

      Pages 121-134

   3. A Tool for the Management of Incomplete Theories: Reasoning about Explanation

      • Béatrice Duval, Yves Kodratoff

      Pages 135-158

   4. A Comparison of Rule and Exemplar-Based Learning Systems

      • Peter Clark

      Pages 159-186

   5. Discovery and Revision via Incremental Hill Climbing

      • Donald Rose

      Pages 187-206

   6. Learning from Imperfect Data

      • Pavel Brazdil, Peter Clark

      Pages 207-232

5. Foundations of AI and Machine Learning

   1. Front Matter

      Pages 233-233

      PDF

   2. Knowledge Revision and Multiple Extensions

      • Camilla B. Schwind

      Pages 235-255

   3. Minimal Change — A Criterion for Choosing between Competing Models

      • Ken Satoh

      Pages 257-276

   4. Hierarchic Autoepistemic Theories for Nonmonotonic Reasoning: Preliminary Report

      • Kurt Konolige

      Pages 277-299

   5. Automated Quantified Modal Logic

      • L. Fariñas del Cerro, A. Herzig

      Pages 301-317

6. Back Matter

   Pages 319-328

   PDF

This book contains a selection of papers presented at the International Workshop Machine Learning, Meta-Reasoning and Logics held in Hotel de Mar in Sesimbra, Portugal, 15-17 February 1988. All the papers were edited afterwards. The Workshop encompassed several fields of Artificial Intelligence: Machine Learning, Belief Revision, Meta-Reasoning and Logics. The objective of this Workshop was not only to address the common issues in these areas, but also to examine how to elaborate cognitive architectures for systems capable of learning from experience, revising their beliefs and reasoning about what they know. Acknowledgements The editing of this book has been supported by COST-13 Project Machine Learning and Knowledge Acquisition funded by the Commission o/the European Communities which has covered a substantial part of the costs. Other sponsors who have supported this work were Junta Nacional de lnvestiga~ao Cientlfica (JNICT), lnstituto Nacional de lnvestiga~ao Cientlfica (INIC), Funda~ao Calouste Gulbenkian. I wish to express my gratitude to all these institutions. Finally my special thanks to Paula Pereira and AnaN ogueira for their help in preparing this volume. This work included retyping all the texts and preparing the camera-ready copy. Introduction 1 1. Meta-Reasoning and Machine Learning The first chapter is concerned with the role meta-reasoning plays in intelligent systems capable of learning. As we can see from the papers that appear in this chapter, there are basically two different schools of thought.

• Extension
• artificial intelligence
• autonom
• knowledge
• learning
• machine learning
• nonmonotonic reasoning

• University of Porto, Portugal

  Pavel B. Brazdil

• SRI International, USA

  Kurt Konolige

Policies and ethics