364 search results - page 51 / 73 » Regularization Learning of Neural Networks for Generalizatio... |
137
Voted
JMLR
2012
13 years 5 months ago
2012
We transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model th...
97
Voted
IJCNN
2006
IEEE
15 years 8 months ago
2006
IEEE
— In this paper we present a method of sequential speech enhancement, where we infer clean speech signal using a Rao-Blackwellized particle filter (RBPF), given a noisecontamina...
131
click to vote
IJCNN
2006
IEEE
15 years 8 months ago
2006
IEEE
— From the Bayesian Ying-Yang (BYY) harmony learning theory, a harmony function has been developed for finite mixtures with a novel property that its maximization can make model...
119
click to vote
ML
2006
ACM
15 years 2 months ago
2006
ACM
Backpropagation, similar to most learning algorithms that can form complex decision surfaces, is prone to overfitting. This work presents classification-based objective functions, ...
134
Voted
CIKM
2011
Springer
14 years 2 months ago
2011
Springer
Traditional feature selection methods assume that the data are independent and identically distributed (i.i.d.). In real world, tremendous amounts of data are distributed in a net...