2924 search results - page 377 / 585 » On the Use of Evidence in Neural Networks |
162
click to vote
ICANN
2009
Springer
15 years 11 months ago
2009
Springer
Recent research has shown that the provisional count of votes of an ensemble of classifiers can be used to estimate the probability that the final ensemble prediction coincides w...
255
click to vote
ICANN
2001
Springer
15 years 11 months ago
2001
Springer
Humans tend to group together related properties in order to understand complex phenomena. When modeling large problems with limited representational resources, it is important to...
161
click to vote
IJCNN
2000
IEEE
15 years 11 months ago
2000
IEEE
This paper examines the computational role of inhibition as it moves towards balancing concurrent excitation using the biologically-inspired Temporal Noisy-Leaky Integrator (TNLI) ...
160
click to vote
IJCNN
2000
IEEE
15 years 11 months ago
2000
IEEE
Many machine learning algorithms can be formulated as the minimization of a training criterion which involves (1) \training errors" on each training example and (2) some hype...
145
click to vote
IWANN
1999
Springer
15 years 11 months ago
1999
Springer
Abstract: Support vector machines (SVMs) are primarily designed for 2-class classification problems. Although in several papers it is mentioned that the combination of K SVMs can b...