1106 search results - page 13 / 222 » On regularization algorithms in learning theory |
ESANN
2008
14 years 11 months ago
2008
The Sensitivity-Based Linear Learning Method (SBLLM) is a learning method for two-layer feedforward neural networks, based on sensitivity analysis, that calculates the weights by s...
NIPS
2008
14 years 11 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...
113
click to vote
JMLR
2006
14 years 9 months ago
2006
We propose a family of learning algorithms based on a new form of regularization that allows us to exploit the geometry of the marginal distribution. We focus on a semi-supervised...
MLG
2007
Springer
15 years 4 months ago
2007
Springer
We give a universal kernel that renders all the regular languages linearly separable. We are not able to compute this kernel efficiently and conjecture that it is intractable, but...
NIPS
2001
14 years 11 months ago
2001
Abstract--Kernel-based algorithms such as support vector machines have achieved considerable success in various problems in batch setting, where all of the training data is availab...