2924 search results - page 230 / 585 » On the Use of Evidence in Neural Networks |
174
click to vote
CORR
2010
Springer
15 years 6 months ago
2010
Springer
Artificial neural networks (ANNs) have been successfully applied to solve a variety of classification and function approximation problems. Although ANNs can generally predict bett...
165
click to vote
NECO
2007
15 years 6 months ago
2007
It is well-known that, in unidentifiable models, the Bayes estimation provides much better generalization performance than the maximum likelihood (ML) estimation. However, its ac...
158
click to vote
IJCNN
2000
IEEE
15 years 11 months ago
2000
IEEE
A product unit is a formal neuron that multiplies its input values instead of summingthem. Furthermore, it has weights acting as exponents instead of being factors. We investigate...
183
click to vote
ICANNGA
2009
Springer
16 years 1 months ago
2009
Springer
In this paper we present application of genetic programming (GP) [1] to evolution of indirect encoding of neural network weights. We compare usage of original HyperNEAT algorithm w...
172
click to vote
ATAL
2008
Springer
15 years 8 months ago
2008
Springer
Due to computational intractability, large scale coordination algorithms are necessarily heuristic and hence require tuning for particular environments. In domains where character...