1419 search results - page 103 / 284 » Approximation Methods for Supervised Learning |
115
Voted
ECML
2007
Springer
15 years 6 months ago
2007
Springer
L1 regularization is effective for feature selection, but the resulting optimization is challenging due to the non-differentiability of the 1-norm. In this paper we compare state...
113
Voted
AAAI
2011
14 years 16 days ago
2011
In this paper we propose differential eligibility vectors (DEV) for temporal-difference (TD) learning, a new class of eligibility vectors designed to bring out the contribution of...
116
click to vote
NIPS
2008
15 years 1 months ago
2008
In this paper we consider approximate policy-iteration-based reinforcement learning algorithms. In order to implement a flexible function approximation scheme we propose the use o...
84
Voted
NN
2008
Springer
15 years 14 days ago
2008
Springer
Currently, there is a lack of general-purpose in-place learning networks that model feature layers in the cortex. By "general-purpose" we mean a general yet adaptive hig...
111
Voted
CDC
2010
IEEE
14 years 7 months ago
2010
IEEE
The asymptotic behavior of stochastic gradient algorithms is studied. Relying on some results of differential geometry (Lojasiewicz gradient inequality), the almost sure pointconve...