Computational Learning Theory and Natural Learning Systems

Intersections between Theory and Experiment
Volume 2
Overview

As with Volume I, this second volume represents a synthesis of issues in three historically distinct areas of learning research: computational learning theory, neural network research, and symbolic machine learning. While the first volume provided a forum for building a science of computational learning across fields, this volume attempts to define plausible areas of joint research: the contributions are concerned with finding constraints for theory while at the same time interpreting theoretic results in the context of experiments with actual learning systems. Subsequent volumes will focus on areas identified as research opportunities.

Computational learning theory, neural networks, and AI machine learning appear to be disparate fields; in fact they have the same goal: to build a machine or program that can learn from its environment. Accordingly, many of the papers in this volume deal with the problem of learning from examples. In particular, they are intended to encourage discussion between those trying to build learning algorithms (for instance, algorithms addressed by learning theoretic analyses are quite different from those used by neural network or machine-learning researchers) and those trying to analyze them.

The first section provides theoretical explanations for the learning systems addressed, the second section focuses on issues in model selection and inductive bias, the third section presents new learning algorithms, the fourth section explores the dynamics of learning in feedforward neural networks, and the final section focuses on the application of learning algorithms.

A Bradford Book

Table of Contents

  1. Preface
  2. Introduction
  3. List of Contributors
  4. 1. Bayes Decisions in a Neural Network-PAC Setting

    Svetlana Anulova, Jorge R. Cuellar, Klaus-U. Hoffgen and Hans-U. Simon

  5. 2. Average Case Analysis of k-CNF and k-DNF Learning Algorithms

    Daniel S. Hirschberg, Michael J. azzani and Kamal M. Ali

  6. 3. Filter Lielihoods and Exhaustive Learning

    David H. Wolpert

  7. 4. Incorporating Prior Knowledge into Networks of Locally-Tuned Units

    Martin Roscheisen, Reimar Hofmann and Volker Tresp

  8. 5. Using Knowledge-Based Neural Networks to Refine Roughtly-correct Information

    Geoffrey G. Towell and Jude W. Shavlik

  9. 6. Sensitivity Constraints in Learning

    Scott H. Clearwater and Yongwon Lee

  10. 7. Evaluation of Learning Biases Using Probalbillistic Domain Knowledge

    Marie desJardins

  11. 8. Detecting sturcture in Small Datasets by Network Fitting under Complexity Constraints

    W. Finnoff and H.G. Zimmermann

  12. 9. Associative Methods in Reinforcement Learning: An Emirical Study

    Leslie Pack Kaelbling

  13. 10. A Schema for Using Multiple Knowledge

    Matjaz Gams, Marko Bohanec and Bojan Cestnik

  14. 11. Probabilistic Hill-Climbing

    William W. Cohen, Russell Greiner and Dale Schuurmans

  15. 12. Prototype Selection Using Competitive Learning

    Michael Lemmon

  16. 13. Learning with Instance-Based Encodings

    Henry Tirri

  17. 14. Contrastive Learning with Graded Random Networks

    javier R. Movellan and James L. McClelland

  18. 15. Probability Density Estimation and Local Basis Function Neural Networks

    Padhraic Smyth

  19. 16. Hamiltonian Dynamics of Neural Networks

    Ulrich Ramacher

  20. 17. Learning Properties of Multi-Layer Perceptrons with and without Feedback

    D. Gawronska, B. Schurmann and J. Hollatz

  21. 18. Unsupervised Learning for Mobile Robot Navigatio Using Probabilistic Data Association

    Ingemar J. Cox and John J. Leonard

  22. 19. Evolution of a Subsumption Architecture that Performs a Wall Following Task for an Autonomous Mobile Robot

    John R. Koza

  23. 20. A connectionist Model of the Learning of Personal Pronouns in English

    Thomas R. Shultz,David Buckingham and Yuriko Oshima-Tankane

  24. 21. Neural Network Modeling of Phsiological Processes

    Volker Tresp, John Moody and Wolf-Rudiger Delong

  25. 22. Projection Pursuit Learning: Some Theoretical Issues

    Ying Zhao and Christopher G. Atkeson

  26. 23. A comparative Study of the Kohonen Self-Organizing Map and the Elastic Net

    Yiu-fai Wong

  27. References
  28. Index