A symbolic representation that decomposes piecewise-linear neural networks into affine functions enables exact weakest-precondition visualization, bounded model checking, and weight-based patching of trained networks.
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 Symbolic Neural Network Representation and its Application to Understanding, Verifying, and Patching Networks
A symbolic representation that decomposes piecewise-linear neural networks into affine functions enables exact weakest-precondition visualization, bounded model checking, and weight-based patching of trained networks.