Sciweavers

1080 search results - page 64 / 216
» Hedging predictions in machine learning
Sort
View
CORR
2006
Springer
111views Education» more  CORR 2006»
15 years 4 months ago
An associative memory for the on-line recognition and prediction of temporal sequences
This paper presents the design of an associative memory with feedback that is capable of on-line temporal sequence learning. A framework for on-line sequence learning has been prop...
Joy Bose, Stephen B. Furber, Jonathan L. Shapiro
ICML
2008
IEEE
16 years 5 months ago
A unified architecture for natural language processing: deep neural networks with multitask learning
We describe a single convolutional neural network architecture that, given a sentence, outputs a host of language processing predictions: part-of-speech tags, chunks, named entity...
Ronan Collobert, Jason Weston
ICML
2005
IEEE
16 years 5 months ago
Efficient discriminative learning of Bayesian network classifier via boosted augmented naive Bayes
The use of Bayesian networks for classification problems has received significant recent attention. Although computationally efficient, the standard maximum likelihood learning me...
Yushi Jing, Vladimir Pavlovic, James M. Rehg
EUROCOLT
1995
Springer
15 years 8 months ago
A decision-theoretic generalization of on-line learning and an application to boosting
k. The model we study can be interpreted as a broad, abstract extension of the well-studied on-line prediction model to a general decision-theoretic setting. We show that the multi...
Yoav Freund, Robert E. Schapire
ICML
2005
IEEE
16 years 5 months ago
A support vector method for multivariate performance measures
This paper presents a Support Vector Method for optimizing multivariate nonlinear performance measures like the F1score. Taking a multivariate prediction approach, we give an algo...
Thorsten Joachims