Algorithmic Learning Theory: 10th International Conference, ALT’99 Tokyo, Japan, December 6–8, 1999 Proceedings

Katharina Morik (auth.), Osamu Watanabe, Takashi Yokomori (eds.)3540667482, 9783540667483

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 :
Tailoring Representations to Different Requirements….Pages 1-12
Theoretical Views of Boosting and Applications….Pages 13-25
Extended Stochastic Complexity and Minimax Relative Loss Analysis….Pages 26-38
Flattening and Implication….Pages 157-168
Induction of Logic Programs Based on ψ -Terms….Pages 169-181
Complexity in the Case Against Accuracy: When Building One Function-Free Horn Clause Is as Hard as Any….Pages 182-193
A Method of Similarity-Driven Knowledge Revision for Type Specializations….Pages 194-205
PAC Learning with Nasty Noise….Pages 206-218
Positive and Unlabeled Examples Help Learning….Pages 219-230
Learning Real Polynomials with a Turing Machine….Pages 231-240
Faster Near-Optimal Reinforcement Learning: Adding Adaptiveness to the E 3 Algorithm….Pages 241-251
Algebraic Analysis for Singular Statistical Estimation….Pages 39-50
Generalization Error of Linear Neural Networks in Unidentifiable Cases….Pages 51-62
The Computational Limits to the Cognitive Power of the Neuroidal Tabula Rasa….Pages 63-76
The Consistency Dimension and Distribution-Dependent Learning from Queries (Extended Abstract)….Pages 77-92
The VC-Dimension of Subclasses of Pattern Languages….Pages 93-105
On the V γ Dimension for Regression in Reproducing Kernel Hilbert Spaces….Pages 106-117
On the Strength of Incremental Learning….Pages 118-131
Learning from Random Text….Pages 132-144
Inductive Learning with Corroboration….Pages 145-156
A Note on Support Vector Machine Degeneracy….Pages 252-263
Learnability of Enumerable Classes of Recursive Functions from “Typical” Examples….Pages 264-275
On the Uniform Learnability of Approximations to Non-recursive Functions….Pages 276-290
Learning Minimal Covers of Functional Dependencies with Queries….Pages 291-300
Boolean Formulas Are Hard to Learn for Most Gate Bases….Pages 301-312
Finding Relevant Variables in PAC Model with Membership Queries….Pages 313-322
General Linear Relations among Different Types of Predictive Complexity….Pages 323-334
Predicting Nearly as Well as the Best Pruning of a Planar Decision Graph….Pages 335-346
On Learning Unions of Pattern Languages and Tree Patterns….Pages 347-363