2075 search results - page 28 / 415 » Learning better transliterations |
117
Voted
GECCO
2007
Springer
15 years 10 months ago
2007
Springer
Imagine a group of cooperating agents attempting to allocate tasks amongst themselves without knowledge of their own capabilities. Over time, they develop a belief of their own sk...
154
click to vote
NN
2010
Springer
14 years 10 months ago
2010
Springer
Appropriately designing sampling policies is highly important for obtaining better control policies in reinforcement learning. In this paper, we first show that the least-squares ...
135
Voted
ICML
2005
IEEE
16 years 4 months ago
2005
IEEE
Hidden Markov Models (HMMs) model sequential data in many fields such as text/speech processing and biosignal analysis. Active learning algorithms learn faster and/or better by cl...
124
Voted
ICML
1996
IEEE
16 years 4 months ago
1996
IEEE
This paper discusses the unsupervised learning problem. An important part of the unsupervised learning problem is determining the numberofconstituent groups (componentsor classes)...
125
click to vote
NIPS
1997
15 years 5 months ago
1997
This paper describes some of the interactions of model learning algorithms and planning algorithms we have found in exploring model-based reinforcement learning. The paper focuses...