986 search results - page 10 / 198 » Zero-data Learning of New Tasks |
MM
2010
ACM
14 years 10 months ago
2010
ACM
The problem of joint modeling the text and image components of multimedia documents is studied. The text component is represented as a sample from a hidden topic model, learned wi...
FLAIRS
2004
14 years 11 months ago
2004
We present results from experiments in using several pitch representations for jazz-oriented musical tasks performed by a recurrent neural network. We have run experiments with se...
ECTEL
2009
Springer
15 years 4 months ago
2009
Springer
Learning Objects are atomic packages of learning content with associated activities that can be reused in different contexts. However traditional Learning Objects can be complex an...
FLAIRS
2007
15 years 1 days ago
2007
Context-sensitive Multiple Task Learning, or csMTL, is presented as a method of inductive transfer that uses a single output neural network and additional contextual inputs for le...
105
click to vote
ICMLA
2009
14 years 7 months ago
2009
One important problem in machine learning is how to extract knowledge from prior experience, then transfer and apply this knowledge in new learning tasks. To address this problem, ...