This book constitutes the refereed proceedings of the 4th European Conference on Computational Learning Theory, EuroCOLT'99, held in Nordkirchen, Germany in March 1999. The 21 revised full papers presented were selected from a total of 35 submissions; also included are two invited contributions. The book is divided in topical sections on learning from queries and counterexamples, reinforcement learning, online learning and export advice, teaching and learning, inductive inference, and statistical theory of learning and pattern recognition.
Author(s): Robert E. Schapire (auth.), Paul Fischer, Hans Ulrich Simon (eds.)
Series: Lecture Notes in Computer Science 1572 : Lecture Notes in Artificial Intelligence
Edition: 1
Publisher: Springer-Verlag Berlin Heidelberg
Year: 1999
Language: English
Pages: 299
Tags: Artificial Intelligence (incl. Robotics); Mathematical Logic and Formal Languages; Algorithm Analysis and Problem Complexity; Computation by Abstract Devices
Theoretical Views of Boosting....Pages 1-10
Open Theoretical Questions in Reinforcement Learning....Pages 11-17
A Geometric Approach to Leveraging Weak Learners....Pages 18-33
Query by Committee, Linear Separation and Random Walks....Pages 34-49
Hardness Results for Neural Network Approximation Problems....Pages 50-62
Learnability of Quantified Formulas....Pages 63-78
Learning Multiplicity Automata from Smallest Counterexamples....Pages 79-90
Exact Learning when Irrelevant Variables Abound....Pages 91-100
An Application of Codes to Attribute-Efficient Learning....Pages 101-110
Learning Range Restricted Horn Expressions....Pages 111-125
On the Asymptotic Behavior of a Constant Stepsize Temporal-Difference Learning Algorithm....Pages 126-137
Direct and Indirect Algorithms for On-line Learning of Disjunctions....Pages 138-152
Averaging Expert Predictions....Pages 153-167
On Teaching and Learning Intersection-Closed Concept Classes....Pages 168-182
Avoiding Coding Tricks by Hyperrobust Learning....Pages 183-197
Mind Change Complexity of Learning Logic Programs....Pages 198-213
Regularized Principal Manifolds....Pages 214-229
Distribution-Dependent Vapnik-Chervonenkis Bounds....Pages 230-240
Lower Bounds on the Rate of Convergence of Nonparametric Pattern Recognition....Pages 241-252
On Error Estimation for the Partitioning Classification Rule....Pages 253-262
Margin Distribution Bounds on Generalization....Pages 263-273
Generalization Performance of Classifiers in Terms of Observed Covering Numbers....Pages 274-285
Entropy Numbers, Operators and Support Vector Kernels....Pages 285-299
