A randomized-learning method that generates hidden-node weights and biases from slope angles and rotations, placing steep sigmoid fragments inside the input space, improves FNN approximation over fixed-interval random parameters.
In: Neural Networks for Conditional Probability Estimation: Forecasting Beyond Point Predictions, chap- ter 6, 87–97, Springer-Verlag London (1999)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving Randomized Learning of Feedforward Neural Networks by Appropriate Generation of Random Parameters
A randomized-learning method that generates hidden-node weights and biases from slope angles and rotations, placing steep sigmoid fragments inside the input space, improves FNN approximation over fixed-interval random parameters.