A modified generation scheme for random weights and biases places sigmoid inflection points inside the input hypercube and optionally makes slope angles uniform, improving fit on two synthetic benchmarks.
Title resolution pending
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
-
Generating Random Parameters in Feedforward Neural Networks with Random Hidden Nodes: Drawbacks of the Standard Method and How to Improve It
A modified generation scheme for random weights and biases places sigmoid inflection points inside the input hypercube and optionally makes slope angles uniform, improving fit on two synthetic benchmarks.