Computational Learning TheoryClarendon Press, 1993 - Artificial intelligence |
Contents
INVITED PAPERS | 1 |
Some new directions in computational learning theory | 19 |
A neuroidal model for cognitive functions by L G Valiant 3333 | 35 |
Copyright | |
10 other sections not shown
Other editions - View all
Common terms and phrases
approximate interpolation assignment binary Boolean classification co-NP compression parameter Computational Learning Theory Computer Science concept class consistent convex polygons counterexample defined definition denote description logic distribution domain embedded non-consensus function equivalence queries expert finite function classes generalises from approximate given graph dimension H validly halfspaces Haussler input integer intermediate form Kullback-Leibler divergence learnable learning algorithm Lemma literals loss bound loss function lower bounds Machine Learning membership queries minimal read-twice DNF monadic logic negative neural net NP-complete outcomes yt output p-concept PAC learnable PAC-learning perceptron polynomial positive example prediction ŷt probabilistic probability problem Proof pseudo-dimension read-twice DNF formulas representation class ripple-down rule sets sample complexity sample length satisfies Schapire sequence subset target concept Theorem trial upper bound validly generalises Vapnik-Chervonenkis dimension variables VC-dimension vector vindicating set w-languages w₁ Warmuth weights Workshop on Computational