1256 search results - page 109 / 252 » Learning to Reason |
132
click to vote
IJCAI
2007
15 years 5 months ago
2007
Most existing sketch understanding systems require a closed domain to achieve recognition. This paper describes an incremental learning technique for opendomain recognition. Our s...
161
click to vote
NIPS
2007
15 years 5 months ago
2007
When we have several related tasks, solving them simultaneously is shown to be more effective than solving them individually. This approach is called multi-task learning (MTL) and...
128
click to vote
VMV
2008
15 years 5 months ago
2008
Machine learning with few training examples always leads to over-fitting problems, whereas human individuals are often able to recognize difficult object categories from only one ...
130
click to vote
WSC
2000
15 years 5 months ago
2000
Web-based study resources can be viewed as a basic requirement in order to remain a competitive player on a more and more globalised educational market. For that reason it is gett...
150
click to vote
CVIU
2008
15 years 4 months ago
2008
We propose a novel scheme for using supervised learning for function-based classification of objects in 3D images. During the learning process, a generic multi-level hierarchical ...