251 search results - page 32 / 51 » Approximation and Estimation Bounds for Artificial Neural Ne... |
ICAI
2007
15 years 1 months ago
2007
Abstract— The paper proposes a dynamic programming algorithm for training of functional networks. The algorithm considers each node as a state. The problem is formulated as find...
124
click to vote
ICANN
2010
Springer
15 years 24 days ago
2010
Springer
Abstract. Learning algorithms relying on Gibbs sampling based stochastic approximations of the log-likelihood gradient have become a common way to train Restricted Boltzmann Machin...
107
click to vote
HAIS
2009
Springer
15 years 4 months ago
2009
Springer
In engineering design the use of approximation models (= surrogate models) has become standard practice for design space exploration, sensitivity analysis, visualization and optimi...
ATAL
2008
Springer
15 years 1 months ago
2008
Springer
Many multiagent domains where cooperation among agents is crucial to achieving a common goal can be modeled as coalitional games. However, in many of these domains, agents are une...
103
click to vote
ICIP
2007
IEEE
16 years 1 months ago
2007
IEEE
In this paper, we propose a learning-based image restoration algorithm for restoring images degraded by uniform motion blurs. The motion blur parameters are first approximately es...