Table of contents (21 papers)

  1. Front Matter
  2. Representing the spatial/kinematic domain and lattice computers
    John Case, Dayanand S. Rajan, Anil M. Shende
    Pages 1-25
  3. Learning decision strategies with genetic algorithms
    John J. Grefenstette
    Pages 35-50
  4. Too much information can be too much for learning efficiently
    Rolf Wiehagen, Thomas Zeugmann
    Pages 72-86
  5. Unions of identifiable classes of total recursive functions
    Kalvis Apsītis, Rūsinš Freivalds, Mārtinš Krikis, Raimonds Simanovskis, Juris Smotrovs
    Pages 99-107
  6. Learning from multiple sources of inaccurate data
    Ganesh Baliga, Sanjay Jain, Arun Sharma
    Pages 108-128
  7. Strong separation of learning classes
    John Case, Keh-Jiann Chen, Sanjay Jain
    Pages 129-139
  8. Desiderata for generalization-to-N algorithms
    William W. Cohen
    Pages 140-150
  9. The power of probabilism in Popperian FINite learning
    Robert Daley, Bala Kalyanasundaram, Mahe Velauthapillai
    Pages 151-169
  10. An inductive inference approach to classification
    Rusins Freivalds, Achim G. Hoffmann
    Pages 187-196
  11. Asking questions versus verifiability
    William I. Gasarch, Mahendran Velauthapillai
    Pages 197-213
  12. Predictive analogy and cognition
    Bipin Indurkhya
    Pages 214-231
  13. A unifying approach to monotonic language learning on informant
    Steffen Lange, Thomas Zeugmann
    Pages 244-259
  14. Characterization of finite identification
    Yasuhito Mukouchi
    Pages 260-267

About these proceedings

Introduction

This volume contains the text of the five invited papers and 16 selected contributions presented at the third International Workshop on Analogical and Inductive Inference, AII `92, held in Dagstuhl Castle, Germany, October 5-9, 1992. Like the two previous events, AII '92 was intended to bring together representatives from several research communities, in particular, from theoretical computer science, artificial intelligence, and from cognitive sciences. The papers contained in this volume constitute a state-of-the-art report on formal approaches to algorithmic learning, particularly emphasizing aspects of analogical reasoning and inductive inference. Both these areas are currently attracting strong interest: analogical reasoning plays a crucial role in the booming field of case-based reasoning, and, in the fieldof inductive logic programming, there have recently been developed a number of new techniques for inductive inference.

Keywords

Cognitive science algorithm algorithms artificial intelligence case-based reasoning intelligence learning logic logical reasoning programming

Bibliographic information

  • Copyright Information Springer-Verlag 1992
  • Publisher Name Springer, Berlin, Heidelberg
  • eBook Packages Springer Book Archive
  • Print ISBN 978-3-540-56004-3
  • Online ISBN 978-3-540-47339-8
  • Series Print ISSN 0302-9743
  • Series Online ISSN 1611-3349