4128 search results - page 303 / 826 » Learning and using relational theories |
143
click to vote
IEAAIE
2004
Springer
16 years 2 days ago
2004
Springer
This paper proposes extending semi-supervised learning by allowing an ongoing interaction between a user and the system. The extension is intended to not only to speed up search fo...
190
click to vote
DAGM
2007
Springer
15 years 10 months ago
2007
Springer
Abstract. In this article we present EANT2, a method that creates neural networks (NNs) by evolutionary reinforcement learning. The structure of NNs is developed using mutation ope...
159
click to vote
IJCAI
2007
15 years 8 months ago
2007
A long-lived agent continually faces new tasks in its environment. Such an agent may be able to use knowledge learned in solving earlier tasks to produce candidate policies for it...
188
click to vote
AAAI
1998
15 years 8 months ago
1998
Automatedreasoning or theorem proving essentially amounts to solving search problems. Despite significant progress in recent years theorem provers still have manyshortcomings. The...
160
click to vote
ICAI
2009
15 years 4 months ago
2009
The authors extended the idea of training multiple tasks simultaneously on a partially shared feed forward network. A shared input subvector was added to represented common inputs...