Algorithmic Learning Theory : 9th International Conference, ALT'98, Otzenhausen, Germany, October 8-10, 1998 Proceedings / edited by Michael M. Richter, Carl H. Smith, Rolf Wiehagen, Thomas Zeugmann.

Format:

Book

Contributor:

Richter, Michael M., 1938- editor.

Smith, Carl H. (Carl Henry), 1895- editor.

Wiehagen, Rolf, editor.

Zeugmann, Thomas, editor.

SpringerLink (Online service)

Series:

Computer Science (Springer-11645)

Lecture notes in computer science. Lecture notes in artificial intelligence ; 1501.

Lecture Notes in Artificial Intelligence ; 1501

Language:

English

Subjects (All):

Computers.

Artificial intelligence.

Logic, Symbolic and mathematical.

Algorithms.

Theory of Computation.

Artificial Intelligence.

Mathematical Logic and Formal Languages.

Algorithm Analysis and Problem Complexity.

Local Subjects:

Theory of Computation.

Artificial Intelligence.

Mathematical Logic and Formal Languages.

Algorithm Analysis and Problem Complexity.

Physical Description:

1 online resource (XI, 444 pages) : 1 illustrations.

Edition:

First edition 1998.

Contained In:

Springer eBooks

Place of Publication:

Berlin, Heidelberg : Springer Berlin Heidelberg : Imprint: Springer, 1998.

System Details:

text file PDF

Summary:

This volume contains all the papers presented at the Ninth International Con- rence on Algorithmic Learning Theory (ALT'98), held at the European education centre Europ ̈aisches Bildungszentrum (ebz) Otzenhausen, Germany, October 8{ 10, 1998. The Conference was sponsored by the Japanese Society for Arti cial Intelligence (JSAI) and the University of Kaiserslautern. Thirty-four papers on all aspects of algorithmic learning theory and related areas were submitted, all electronically. Twenty-six papers were accepted by the program committee based on originality, quality, and relevance to the theory of machine learning. Additionally, three invited talks presented by Akira Maruoka of Tohoku University, Arun Sharma of the University of New South Wales, and Stefan Wrobel from GMD, respectively, were featured at the conference. We would like to express our sincere gratitude to our invited speakers for sharing with us their insights on new and exciting developments in their areas of research. This conference is the ninth in a series of annual meetings established in 1990. The ALT series focuses on all areas related to algorithmic learning theory including (but not limited to): the theory of machine learning, the design and analysis of learning algorithms, computational logic of/for machine discovery, inductive inference of recursive functions and recursively enumerable languages, learning via queries, learning by arti cial and biological neural networks, pattern recognition, learning by analogy, statistical learning, Bayesian/MDL estimation, inductive logic programming, robotics, application of learning to databases, and gene analyses.

Contents:

Editors' Introduction

Editors' Introduction

Inductive Logic Programming and Data Mining

Scalability Issues in Inductive Logic Programming

Inductive Inference

Learning to Win Process-Control Games Watching Game-Masters

Closedness Properties in EX-Identification of Recursive Functions

Learning via Queries

Lower Bounds for the Complexity of Learning Half-Spaces with Membership Queries

Cryptographic Limitations on Parallelizing Membership and Equivalence Queries with Applications to Random Self-Reductions

Learning Unary Output Two-Tape Automata from Multiplicity and Equivalence Queries

Computational Aspects of Parallel Attribute-Efficient Learning

PAC Learning from Positive Statistical Queries

Prediction Algorithns

Structured Weight-Based Prediction Algorithms

Inductive Logic Programming

Learning from Entailment of Logic Programs with Local Variables

Logical Aspects of Several Bottom-Up Fittings

Learnability of Translations from Positive Examples

Analysis of Case-Based Representability of Boolean Functions by Monotone Theory

Learning Formal Languages

Locality, Reversibility, and Beyond: Learning Languages from Positive Data

Synthesizing Learners Tolerating Computable Noisy Data

Characteristic Sets for Unions of Regular Pattern Languages and Compactness

Finding a One-Variable Pattern from Incomplete Data

A Fast Algorithm for Discovering Optimal String Patterns in Large Text Databases

A Comparison of Identification Criteria for Inductive Inference of Recursive Real-Valued Functions

Predictive Learning Models for Concept Drift

Learning with Refutation

Comparing the Power of Probabilistic Learning and Oracle Identification Under Monotonicity Constraints

Learning Algebraic Structures from Text Using Semantical Knowledge

Lime: A System for Learning Relations

Miscellaneous

On the Sample Complexity for Neural Trees

Learning Sub-classes of Monotone DNF on the Uniform Distribution

Using Attribute Grammars for Description of Inductive Inference Search Space

Towards the Validation of Inductive Learning Systems

Consistent Polynomial Identification in the Limit.

Other Format:

Printed edition:

ISBN:

978-3-540-49730-1

9783540497301

Access Restriction:

Restricted for use by site license.