Sciweavers

153 search results - page 17 / 31
» An empirical comparison of supervised learning algorithms
Sort
View
JMLR
2010
106views more  JMLR 2010»
14 years 6 months ago
Why Does Unsupervised Pre-training Help Deep Learning?
Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtai...
Dumitru Erhan, Yoshua Bengio, Aaron C. Courville, ...
GECCO
2006
Springer
157views Optimization» more  GECCO 2006»
15 years 3 months ago
gLINC: identifying composability using group perturbation
We present two novel perturbation-based linkage learning algorithms that extend LINC [5]; a version of LINC optimised for decomposition tasks (oLINC) and a hierarchical version of...
David Jonathan Coffin, Christopher D. Clack
111
Voted
ML
2002
ACM
168views Machine Learning» more  ML 2002»
14 years 11 months ago
On Average Versus Discounted Reward Temporal-Difference Learning
We provide an analytical comparison between discounted and average reward temporal-difference (TD) learning with linearly parameterized approximations. We first consider the asympt...
John N. Tsitsiklis, Benjamin Van Roy
ECAI
2008
Springer
15 years 1 months ago
Task Driven Coreference Resolution for Relation Extraction
Abstract. This paper presents the extension of an existing mimimally supervised rule acquisition method for relation extraction by coreference resolution (CR). To this end, a novel...
Feiyu Xu, Hans Uszkoreit, Hong Li
127
Voted
EMNLP
2011
13 years 11 months ago
Training dependency parsers by jointly optimizing multiple objectives
We present an online learning algorithm for training parsers which allows for the inclusion of multiple objective functions. The primary example is the extension of a standard sup...
Keith Hall, Ryan T. McDonald, Jason Katz-Brown, Mi...