ISBN: 3-540-66748-2
TITLE: Algorithmic Learning Theory
AUTHOR: Watanabe, Osamu; Yokomori, Takashi (Eds.)
TOC:

INVITED LECTURES
Tailoring Representations to Different Requirements 1
Katharina Morik
Theoretical Views of Boosting and Applications 13
Robert E. Schapire
Extended Stochastic Complexity and Minimax Relative Loss Analysis 26
Kenji Yamanishi
REGULAR CONTRIBUTIONS
Neural Networks
Algebraic Analysis for Singular Statistical Estimation 39
Sumio Watanabe
Generalization Error of Linear Neural Networks in Unidentifiable Cases 51
Kenji Fukumizu
The Computational Limits to the Cognitive Power of the Neuroidal Tabula Rasa 63
Jir Wiedermann
Learning Dimension
The Consistency Dimension and Distribution-Dependent Learning from Queries 77
Jos L. Balczar, Jorge Castro, David Guijarro, and Hans-Ulrich Simon
The VC-Dimension of Subclasses of Pattern Languages 93
Andrew Mitchell, Tobias Scheffer, Arun Sharma, and Frank Stephan
On the V_gamma Dimension for Regression in Reproducing Kernel Hilbert
Spaces 106
Theodoros Evgeniou and Massimiliano Pontil
Inductive Inference
On the Strength of Incremental Learning 118
Steffen Lange and Gunter Grieser
Learning from Random Text 132
Peter Rossmanith
Inductive Learning with Corroboration 145
Phil Watson
Inductive Logic Programming
Flattening and Implication 157
Kouichi Hirata
Induction of Logic Programs Based on psi-Terms 169
Yutaka Sasaki
Complexity in the Case Against Accuracy: When Building One Function-Free Horn Clause Is as Hard as Any 182
Richard Nock
A Method of Similarity-Driven Knowledge Revision for Type Specifications 194
Nobuhiro Morita, Makoto Haraguchi, and Yoshiaki Okubo
PAC Learning
PAC Learning with Nasty Noise 206
Nader H. Bshouty, Nadav Eiron, and Eyal Kushilevitz
Positive and Unlabeled Examples Help Learning 219
Francesco De Comit, Franois Denis, Rmi Gilleron, and Fabien Letouzey
Learning Real Polynomials with a Turing Machine 231
Dennis Cheung
Mathematical Tools for Learning
Faster Near-Optimal Reinforcement Learning: Adding Adaptiveness to the E^3 Algorithm 241
Carlos Domingo
A Note on Support Vector Machine Degeneracy 252
Ryan Rifkin, Massimiliano Pontil, and Alessandro Verri
Learning Recursive Functions
Learnability of Enumerable Classes of Recursive Functions from "Typical" Examples 264
Jochen Nessel
On the Uniform Learnability of Approximations to Non-recursive Functions 276
Frank Stephan and Thomas Zeugmann
Query Learning
Learning Minimal Covers of Functional Dependencies with Queries 291
Montserrat Hermo and Vctor Lavn
Boolean Formulas Are Hard to Learn for Most Gate Bases 301
Vctor Dalmau
Finding Relevant Variables in PAC Model with Membership Queries 313
David Guijarro, Jun Tarui, and Tatsuie Tsukiji
On-Line Learning
General Linear Relations among Different Types of Predictive Complexity 323
Yuri Kalnishkan
Predicting Nearly as Well as the Best Pruning of a Planar Decision Graph 335
Eiji Takimoto and Manfred K. Warmuth
On Learning Unions of Pattern Languages and Tree Patterns 347
Sally A. Goldman and Stephen S. Kwek
Author Index 365
END
