Sparse MLPs trained via SET plus neuron pruning achieve competitive performance on 15 datasets while pruning ~50% of hidden neurons and keeping parameter count linear in neuron count.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On improving deep learning generalization with adaptive sparse connectivity
Sparse MLPs trained via SET plus neuron pruning achieve competitive performance on 15 datasets while pruning ~50% of hidden neurons and keeping parameter count linear in neuron count.