An iterative threshold-based node selection scheme for data-driven randomized feedforward networks produces more compact architectures and faster error reduction than the non-constructive baseline.
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
-
A Constructive Approach for Data-Driven Randomized Learning of Feedforward Neural Networks
An iterative threshold-based node selection scheme for data-driven randomized feedforward networks produces more compact architectures and faster error reduction than the non-constructive baseline.