A BinaryConnect-style method with 0/1 weights learns sparse topologies that retain near-baseline accuracy and tolerate constant weight rescaling, interpreted as NOR-gate digital circuits.
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
-
Learning Digital Circuits: A Journey Through Weight Invariant Self-Pruning Neural Networks
A BinaryConnect-style method with 0/1 weights learns sparse topologies that retain near-baseline accuracy and tolerate constant weight rescaling, interpreted as NOR-gate digital circuits.