Algorithmic Learning Theory: 10th International Conference, Alt'99, Tokyo, Japan, December 6-8, 1999, Proceedings

by Alt'9 (1999 Tokyo, Japan); Yokomori, Takashi; Carbonell, J. G.; Siekmann, J.; Watanabe, Osamu

• ISBN13: 9783540667483
• ISBN10: 3540667482
• Format: Paperback
• Copyright: 2000-01-01
• Publisher: Springer Verlag

Summary

This book constitutes the refereed proceedings of the 10th International Conference on Algorithmic Learning Theory, ALT'99, held in Tokyo, Japan, in December 1999.The 26 full papers presented were carefully reviewed and selected from a total of 51 submissions. Also included are three invited papers. The papers are organized in sections on Learning Dimension, Inductive Inference, Inductive Logic Programming, PAC Learning, Mathematical Tools for Learning, Learning Recursive Functions, Query Learning and On-Line Learning.

Table of Contents

Invited Lectures
Tailoring Representations to Different Requirements	p. 1
Theoretical Views of Boosting and Applications	p. 13
Extended Stochastic Complexity and Minimax Relative Loss Analysis	p. 26
Regular Contributions
Neural Networks
Algebraic Analysis for Singular Statistical Estimation	p. 39
Generalization Error of Linear Neural Networks in Unidentifiable Cases	p. 51
The Computational Limits to the Cognitive Power of the Neuroidal Tabula Rasa	p. 63
Learning Dimension
The Consistency Dimension and Distribution-Dependent Learning from Queries	p. 77
The VC-Dimension of Subclasses of Pattern Languages	p. 93
On the V¿ Dimension for Regression in Reproducing Kernel Hilbert Spaces	p. 106
Inductive Inference
On the Strength of Incremental Learning	p. 118
Learning from Random Text	p. 132
Inductive Learning with Corroboration	p. 145
Inductive Logic Programming
Flattening and Implication	p. 157
Induction of Logic Programs Based on ¿-Terms	p. 169
Complexity in the Case Against Accuracy: When Building One Function-Free Horn Clause Is as Hard as Any	p. 182
A Method of Similarity-Driven Knowledge Revision for Type Specifications	p. 194
PAC Learning
PAC Learning with Nasty Noise	p. 206
Positive and Unlabeled Examples Help Learning	p. 219
Learning Real Polynomials with a Turing Machine	p. 231
Mathematical Tools for Learning
Faster Near-Optimal Reinforcement Learning: Adding Adaptiveness to the E3 Algorithm	p. 241
A Note on Support Vector Machine Degeneracy	p. 252
Learning Recursive Functions
Learnability of Enumerable Classes of Recursive Functions from "Typical" Examples	p. 264
On the Uniform Learnability of Approximations to Non-recursive Functions	p. 276
Query Learning
Learning Minimal Covers of Functional Dependencies with Queries	p. 291
Boolean Formulas Are Hard to Learn for Most Gate Bases	p. 301
Finding Relevant Variables in PAC Model with Membership Queries	p. 313
On-Line Learning
General Linear Relations among Different Types of Predictive Complexity	p. 323
Predicting Nearly as Well as the Best Pruning of a Planar Decision Graph	p. 335
On Learning Unions of Pattern Languages and Tree Patterns	p. 347
Author Index	p. 365
Table of Contents provided by Publisher. All Rights Reserved.