986 search results - page 61 / 198 » Zero-data Learning of New Tasks |
116
Voted
NN
2006
Springer
15 years 3 months ago
2006
Springer
This paper presents an on-line unsupervised learning mechanism for unlabeled data that are polluted by noise. Using a similarity thresholdbased and a local error-based insertion c...
142
Voted
JMLR
2010
14 years 10 months ago
2010
We present a new approximate inference algorithm for Deep Boltzmann Machines (DBM's), a generative model with many layers of hidden variables. The algorithm learns a separate...
159
Voted
AAAI
2012
13 years 6 months ago
2012
Selecting the optimal kernel is an important and difficult challenge in applying kernel methods to pattern recognition. To address this challenge, multiple kernel learning (MKL) ...
143
Voted
ISCI
2007
15 years 3 months ago
2007
In this paper we study supervised and semi-supervised classification of e-mails. We consider two tasks: filing e-mails into folders and spam e-mail filtering. Firstly, in a sup...
131
Voted
MICCAI
1999
Springer
15 years 8 months ago
1999
Springer
We present a new metaphor for learning anatomy - the 3d puzzle. With this metaphor students learn anatomic relations by assembling a geometric model themselves. For this purpose, a...