7928 search results - page 80 / 1586 » Human-Like Learning Methods for a |
119
click to vote
PRL
2011
14 years 6 months ago
2011
In some real world applications, such as spectrometry, functional models achieve better predictive performances if they work on the derivatives of order m of their inputs rather t...
NAACL
2007
15 years 1 months ago
2007
Customization to specific domains of discourse and/or user requirements is one of the greatest challenges for today’s Information Extraction (IE) systems. While demonstrably eff...
119
click to vote
CVPR
2011
IEEE
14 years 7 months ago
2011
IEEE
We propose a new learning method which exploits temporal consistency to successfully learn a complex appearance model from a sparsely labeled training video. Our approach consists...
105
click to vote
NAACL
2010
14 years 9 months ago
2010
Taxonomies are an important resource for a variety of Natural Language Processing (NLP) applications. Despite this, the current stateof-the-art methods in taxonomy learning have d...
105
click to vote
AAAI
2011
13 years 12 months ago
2011
Automated feature discovery is a fundamental problem in machine learning. Although classical feature discovery methods do not guarantee optimal solutions in general, it has been r...