ICML
2008
IEEE
2008
IEEE
A unified architecture for natural language processing: deep neural networks with multitask learning
14 years 5 months ago
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...
ICML
2008
IEEE
14 years 5 months ago
2008
IEEE
Multi-view learning has become a hot topic during the past few years. In this paper, we first characterize the sample complexity of multi-view active learning. Under the expansion...
ICML
2008
IEEE
14 years 5 months ago
2008
IEEE
Semi-supervised learning aims at taking advantage of unlabeled data to improve the efficiency of supervised learning procedures. For discriminative models however, this is a chall...
ICML
2007
IEEE
14 years 5 months ago
2007
IEEE
Multi-instance learning and semi-supervised learning are different branches of machine learning. The former attempts to learn from a training set consists of labeled bags each con...
ICPR
2006
IEEE
14 years 5 months ago
2006
IEEE
Many classification tasks benefit from integrating manifold learning and semi-supervised learning. By formulating the learning task in a semi-supervised manner, we propose a novel...
CVPR
2007
IEEE
14 years 6 months ago
2007
IEEE
Recent research in visual inference from monocular images has shown that discriminatively trained image-based predictors can provide fast, automatic qualitative 3D reconstructions...
CVPR
2005
IEEE
14 years 6 months ago
2005
IEEE
The appearance of dynamic scenes is often largely governed by a latent low-dimensional dynamic process. We show how to learn a mapping from video frames to this lowdimensional rep...
CVPR
2005
IEEE
14 years 6 months ago
2005
IEEE
Although recent studies have shown that unlabeled data are beneficial to boosting the image retrieval performance, very few approaches for image retrieval can learn with labeled a...