1989 search results - page 272 / 398 » Learning to Select Useful Landmarks |
170
click to vote
ICMLA
2008
15 years 7 months ago
2008
We revisit 26 meta-features typically used in the context of meta-learning for model selection. Using visual analysis and computational complexity considerations, we find 4 meta-f...
166
click to vote
CONNECTION
2004
15 years 6 months ago
2004
: High capacity associative neural networks can be built from networks of perceptrons, trained using simple perceptron training. Such networks perform much better than those traine...
146
click to vote
NAACL
2010
15 years 4 months ago
2010
In this paper we report a behavioural experiment documenting that different lexicosyntactic formulations of the discourse relation of causation are deemed more or less acceptable ...
163
click to vote
ECML
2007
Springer
16 years 11 days ago
2007
Springer
L1 regularization is effective for feature selection, but the resulting optimization is challenging due to the non-differentiability of the 1-norm. In this paper we compare state...
153
click to vote
WCAE
2006
ACM
16 years 4 days ago
2006
ACM
At Northeastern University we are building a number of courses upon a common embedded systems platform. The goal is to reduce the learning curve associated with new architectures ...