Sciweavers

290 search results - page 23 / 58
» The Iterated Version Space Learning
Sort
View
NN
2000
Springer
192views Neural Networks» more  NN 2000»
13 years 7 months ago
A new algorithm for learning in piecewise-linear neural networks
Piecewise-linear (PWL) neural networks are widely known for their amenability to digital implementation. This paper presents a new algorithm for learning in PWL networks consistin...
Emad Gad, Amir F. Atiya, Samir I. Shaheen, Ayman E...
COLT
2007
Springer
13 years 11 months ago
An Efficient Re-scaled Perceptron Algorithm for Conic Systems
Abstract. The classical perceptron algorithm is an elementary algorithm for solving a homogeneous linear inequality system Ax > 0, with many important applications in learning t...
Alexandre Belloni, Robert M. Freund, Santosh Vempa...
IJCAI
2007
13 years 9 months ago
Kernel Conjugate Gradient for Fast Kernel Machines
We propose a novel variant of the conjugate gradient algorithm, Kernel Conjugate Gradient (KCG), designed to speed up learning for kernel machines with differentiable loss functio...
Nathan D. Ratliff, J. Andrew Bagnell
ALT
2007
Springer
14 years 1 months ago
Online Regression Competitive with Changing Predictors
This paper deals with the problem of making predictions in the online mode of learning where the dependence of the outcome yt on the signal xt can change with time. The Aggregating...
Steven Busuttil, Yuri Kalnishkan
ALT
2003
Springer
13 years 11 months ago
Can Learning in the Limit Be Done Efficiently?
Abstract. Inductive inference can be considered as one of the fundamental paradigms of algorithmic learning theory. We survey results recently obtained and show their impact to pot...
Thomas Zeugmann