536 search results - page 70 / 108 » Residual Algorithms: Reinforcement Learning with Function Ap... |
135
Voted
ICML
2010
IEEE
15 years 3 months ago
2010
IEEE
Restricted Boltzmann Machines (RBMs) are a type of probability model over the Boolean cube {-1, 1}n that have recently received much attention. We establish the intractability of ...
121
Voted
ECCV
2004
Springer
16 years 4 months ago
2004
Springer
This paper proposes a robust estimation and validation framework for characterizing local structures in a positive multi-variate continuous function approximated by a Gaussian-base...
98
Voted
PAMI
2008
15 years 2 months ago
2008
In this paper, we develop a new effective multiple kernel learning algorithm. First, we map the input data into m different feature spaces by m empirical kernels, where each genera...
117
Voted
ICML
2008
IEEE
16 years 3 months ago
2008
IEEE
Identifying the appropriate kernel function/matrix for a given dataset is essential to all kernel-based learning techniques. A variety of kernel learning algorithms have been prop...
143
Voted
PKDD
2010
Springer
15 years 20 days ago
2010
Springer
Abstract. We present a novel approach for classification using a discretised function representation which is independent of the data locations. We construct the classifier as a su...