Computational Learning Theory: EuroCOLT '93
John Shawe-Taylor, Martin Anthony
Oxford University Press, USA, Oct 27, 1994 - Computational learning theory - 256 pages
The study of machine learning within the mathematical framework of complexity theory has seen great strides in just a few short years, spurred on by the tremendous rise in interest from engineers studying control to analysts predicting financial market activity. Based on the first European Conference on Computational Learning Theory, and including a number of invited contributions, Computational Learning Theory offers an outstanding overview of the subject, with topics ranging from results inspired by neural network research to those originating from more classical artificial intelligence approaches. It will appeal to students and researchers in applied mathematics, computer science, and cognitive science.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Some new directions in computational learning theory
A neuroidal model for cognitive functions by L G Valiant
6 other sections not shown
approximate interpolation arbitrary assignment assume B-type binary Boolean classification co-NP compression parameter Computational Learning Theory Computer Science concept class consider consistent convex polygons counterexample decision lists defined definition denote Department of Computer depth description logic deterministic distribution domain equivalence queries expert function classes gate generalisation from approximate given graph halfspaces Haussler hypothesis h input integer learning algorithm learning model Lemma linear literals loss function lower bounds Machine Learning membership queries monadic logic negative neural nets neural network nodes non-consensus function NP-complete outcomes yt output p-concept PAB-decision PAC learnable PAC-learning perceptron polynomial positive data positive example probabilistic probability Proc Proof pseudo-dimension read-twice DNF formulas representation representation class ripple-down rule set sample complexity satisfies sequence stochastic rules subset target concept Theorem threshold trial upper bound validly generalises Vapnik-Chervonenkis dimension variables VC-dimension vector w-languages Warmuth weights Workshop on Computational