3624 search results - page 212 / 725 » Learning to learn: From smart machines to intelligent machin... |
174
click to vote
FLAIRS
2010
15 years 9 months ago
2010
We present context-sensitive Multiple Task Learning, or csMTL as a method of inductive transfer. It uses additional contextual inputs along with other input features when learning ...
126
click to vote
ICALT
2005
IEEE
16 years 7 days ago
2005
IEEE
Based on our findings from an ongoing pilot with shared computers in rural primary schools in Uttar Pradesh, India since 2001 and two follow-up field studies in the same schools i...
209
click to vote
COLING
2000
15 years 8 months ago
2000
We present some novel machine learning techniques for the identification of subcategorization information for verbs in Czech. We compare three different statistical techniques app...
146
click to vote
CORR
2002
Springer
15 years 6 months ago
2002
Springer
In this paper, we review five heuristic strategies for handling context-sensitive features in supervised machine learning from examples. We discuss two methods for recovering lost...
170
click to vote
MLDM
2005
Springer
16 years 3 days ago
2005
Springer
We estimate the speed of texture change by measuring the spread of texture vectors in their feature space. This method allows us to robustly detect even very slow moving objects. B...