Dudek proposes setting the weights and biases of random hidden-layer sigmoids using local linear fits to the target function, and shows improved regression accuracy on a synthetic function and two real datasets.
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
-
Data-Driven Randomized Learning of Feedforward Neural Networks
Dudek proposes setting the weights and biases of random hidden-layer sigmoids using local linear fits to the target function, and shows improved regression accuracy on a synthetic function and two real datasets.