5860 search results - page 165 / 1172 » Learning and Domain Adaptation |
194
click to vote
COLING
2010
15 years 2 months ago
2010
We describe a new unsupervised approach for synonymy discovery by aligning paraphrases in monolingual domain corpora. For that purpose, we identify phrasal terms that convey most ...
192
Voted
EWRL
2008
15 years 8 months ago
2008
Two variable metric reinforcement learning methods, the natural actor-critic algorithm and the covariance matrix adaptation evolution strategy, are compared on a conceptual level a...
200
Voted
ICST
2008
IEEE
16 years 1 months ago
2008
IEEE
It is becoming increasingly important to be able to adapt an application’s behavior at run time in response to changing requirements and environmental conditions. Adaptive progr...
288
Voted
ILP
2007
Springer
16 years 1 months ago
2007
Springer
Abstract. Many reinforcement learning domains are highly relational. While traditional temporal-difference methods can be applied to these domains, they are limited in their capaci...
178
Voted
IJIT
2004
15 years 8 months ago
2004
Since the presentation of the backpropagation algorithm, a vast variety of improvements of the technique for training a feed forward neural networks have been proposed. This articl...