151 search results - page 13 / 31 » Optimized Approximation Algorithm in Neural Networks Without... |
165
click to vote
NN
2002
Springer
15 years 5 months ago
2002
Springer
When learning a mixture model, we suffer from the local optima and model structure determination problems. In this paper, we present a method for simultaneously solving these prob...
196
click to vote
NPL
2006
15 years 5 months ago
2006
In multi-instance learning, the training examples are bags composed of instances without labels, and the task is to predict the labels of unseen bags through analyzing the training...
164
click to vote
GECCO
2009
Springer
15 years 10 months ago
2009
Springer
Encouraging exploration, typically by preserving the diversity within the population, is one of the most common method to improve the behavior of evolutionary algorithms with dece...
168
click to vote
STOC
1993
ACM
15 years 10 months ago
1993
ACM
Abstract. It is shown that high-order feedforward neural nets of constant depth with piecewisepolynomial activation functions and arbitrary real weights can be simulated for Boolea...
150
click to vote
IPMU
2010
Springer
15 years 9 months ago
2010
Springer
Abstract. Credal sets are closed convex sets of probability mass functions. The lower probabilities specified by a credal set for each element of the power set can be used as cons...