Computational Learning Theory
Published on 1. September 1994
Book
Hardback
250 pages
978-0-19-853492-1 (ISBN)
Description
This volume contains 17 of the contributed papers presented at the 1st European Conference on Computational Learning Theory. Also included are invited presentations on the complexity of learning on neural nets, on new directions in computational learning theory, and on a neurodial model for cognitive functions. The proceedings give an overview of current work in computational learning theory, ranging from results inspired by neural network research to those arising from more classical artificial intelligence approaches. The study of machine learning within the mathematical framework of complexity theory has been a relatively recent development. The burgeoning interest in the application of machine learning to a wide variety of problems from control to financial market prediction has fired a corresponding upsurge in mathematical research.
More details
Language
English
Place of publication
Oxford
United Kingdom
Publishing group
Oxford University Press
Target group
College/higher education
Professional and scholarly
Illustrations
line drawings, bibliography
ISBN-13
978-0-19-853492-1 (9780198534921)
Copyright in bibliographic data is held by Nielsen Book Services Limited or its licensors: all rights reserved.
Schweitzer Classification
Persons
Content
W. Maass: On the complexity of learning on neural nets; M. Frazier and L. Pitt: Some new directions in computational learning theory; L.G. Valiant: A neuroidal model for cognitive functions; J. Kivinen, H. Mannila and E. Ukkonen: Learning rules with local exceptions; M. Golea and M. Marchand: On learning simple deterministic and probabilistic neural concepts; P. Fischer: Learning unions of convex polygons; T. Hegedus: On training simple neural networks and small-weight neurons; H.U. Simon: Bounds on the number of examples needed for learning functions; M. Anthony and J. Shawe-Taylor: Valid generalization of functions from close approximations on a sample; J. Kivinen and M.K. Warmuth: Using experts for predicting continuous outcomes; K. Pillaipakkamnatt and V. Raghavan: Read-twice DNF formulas are properly learnable; F. Ameur, P. Fischer, K.U. Hoeffgen and F. Meyer auf der Heide: Trial and error: a new approach to space-bounded learning; S. Anoulova and S. Poelt: Using Kullback-Leibler divergence in learning theory; Saoudi Yokomori: Learning local and recognizable w-languages and monadic logic programs; R. Wiehagen, C.H. Smith and T. Zeugmann: Classification of predicates and languages; H. Wiklicky: The neural network loading problem is undecidable; R. Gavalda: On the power of equivalence; On-line prediction and conversion strategies; K. Yamanishi: Learning non-parametric smooth rules by stochastic rules with finite partitioning; S. Poelt: Improved sample size bounds for PAB-decisions.