12194 search results - page 108 / 2439 » Numberings Optimal for Learning |
157
click to vote
ICML
2009
IEEE
16 years 5 months ago
2009
IEEE
Training principles for unsupervised learning are often derived from motivations that appear to be independent of supervised learning. In this paper we present a simple unificatio...
174
click to vote
SCAI
2008
15 years 5 months ago
2008
Abstract. A reinforcement architecture is introduced that consists of three complementary learning systems with different generalization abilities. The ACTOR learns state-action as...
134
click to vote
NPL
2000
15 years 4 months ago
2000
A backpropagation learning algorithm for feedforward neural networks with an adaptive learning rate is derived. The algorithm is based upon minimising the instantaneous output erro...