Sciweavers

14 search results - page 1 / 3
» Empirical learning aided by weak domain knowledge in the for...
Sort
View
CORR
2010
Springer
104views Education» more  CORR 2010»
13 years 4 months ago
Empirical learning aided by weak domain knowledge in the form of feature importance
Standard hybrid learners that use domain knowledge require stronger knowledge that is hard and expensive to acquire. However, weaker domain knowledge can benefit from prior knowle...
Ridwan Al Iqbal
JMLR
2008
124views more  JMLR 2008»
13 years 4 months ago
Learning Control Knowledge for Forward Search Planning
A number of today's state-of-the-art planners are based on forward state-space search. The impressive performance can be attributed to progress in computing domain independen...
Sung Wook Yoon, Alan Fern, Robert Givan
CORR
2011
Springer
200views Education» more  CORR 2011»
12 years 12 months ago
Using Feature Weights to Improve Performance of Neural Networks
Different features have different relevance to a particular learning problem. Some features are less relevant; while some very important. Instead of selecting the most relevant fe...
Ridwan Al Iqbal
DIS
2005
Springer
13 years 10 months ago
Exploring Predicate-Argument Relations for Named Entity Recognition in the Molecular Biology Domain
In this paper, the semantic relationships between a predicate and its arguments in terms of semantic roles are employed to improve lexical-based named entity recognition (NER) in t...
Tuangthong Wattarujeekrit, Nigel Collier
MLMI
2007
Springer
13 years 11 months ago
Using Prosodic Features in Language Models for Meetings
Abstract. Prosody has been actively studied as an important knowledge source for speech recognition and understanding. In this paper, we are concerned with the question of exploiti...
Songfang Huang, Steve Renals