4930 search results - page 154 / 986 » Learning minimal abstractions |
101
click to vote
NPL
1998
15 years 13 days ago
1998
Adaptive artificial neural network techniques are introduced and applied to the factorization of 2-D second order polynomials. The proposed neural network is trained using a const...
125
Voted
TNN
1998
15 years 13 days ago
1998
—Structural learning with forgetting is an established method of using Laplace regularization to generate skeletal artificial neural networks. In this paper we develop a continu...
117
click to vote
JMLR
2012
13 years 3 months ago
2012
In this paper we address the problem of pool based active learning, and provide an algorithm, called UPAL, that works by minimizing the unbiased estimator of the risk of a hypothe...
170
Voted
ICML
2003
IEEE
16 years 1 months ago
2003
IEEE
An approach to semi-supervised learning is proposed that is based on a Gaussian random field model. Labeled and unlabeled data are represented as vertices in a weighted graph, wit...
113
Voted
IIR
2010
15 years 2 months ago
2010
Given a classifier trained on relatively few training examples, active learning (AL) consists in ranking a set of unlabeled examples in terms of how informative they would be, if ...