This book constitutes the refereed proceedings of the Third European Conference on Computational Learning Theory, EuroCOLT'97, held in Jerusalem, Israel, in March 1997.
The book presents 25 revised full papers carefully selected from a total of 36 high-quality submissions. The volume spans the whole spectrum of computational learning theory, with a certain emphasis on mathematical models of machine learning. Among the topics addressed are machine learning, neural nets, statistics, inductive inference, computational complexity, information theory, and theoretical physics.
Author(s): Manfred Warmuth (auth.), Shai Ben-David (eds.)
Series: Lecture Notes in Computer Science 1208 : Lecture Notes in Artificial Intelligence
Edition: 1
Publisher: Springer-Verlag Berlin Heidelberg
Year: 1997
Language: English
Pages: 338
Tags: Artificial Intelligence (incl. Robotics); Mathematical Logic and Formal Languages; Computation by Abstract Devices
Sample compression, learnability, and the Vapnik-Chervonenkis dimension....Pages 1-2
Learning boxes in high dimension....Pages 3-15
Learning monotone term decision lists....Pages 16-26
Learning matrix functions over rings....Pages 27-37
Learning from incomplete boundary queries using split graphs and hypergraphs....Pages 38-50
Generalization of the PAC-model for learning with partial information....Pages 51-65
Monotonic and dual-monotonic probabilistic language learning of indexed families with high probability....Pages 66-78
Closedness properties in team learning of recursive functions....Pages 79-93
Structural measures for games and process control in the branch learning model....Pages 94-108
Learning under persistent drift....Pages 109-118
Randomized hypotheses and minimum disagreement hypotheses for learning with noise....Pages 119-133
Learning when to trust which experts....Pages 134-149
On learning branching programs and small depth circuits....Pages 150-161
Learning nearly monotone k -term DNF....Pages 162-170
Optimal attribute-efficient learning of disjunction, parity, and threshold functions....Pages 171-184
learning pattern languages using queries....Pages 185-197
On fast and simple algorithms for finding Maximal subarrays and applications in learning theory....Pages 198-209
A minimax lower bound for empirical quantizer design....Pages 210-222
Vapnik-Chervonenkis dimension of recurrent neural networks....Pages 223-237
Linear Algebraic proofs of VC-Dimension based inequalities....Pages 238-250
A result relating convex n-widths to covering numbers with some applications to neural networks....Pages 251-259
Confidence estimates of classification accuracy on new examples....Pages 260-271
Learning formulae from elementary facts....Pages 272-285
Control structures in hypothesis spaces: The influence on learning....Pages 286-300
Ordinal mind change complexity of language identification....Pages 301-315
Robust learning with infinite additional information....Pages 316-330
