A new explanation method for ReLU neural networks that builds piecewise linear models from selected connected subsets of hidden units, called paths, to produce adjustable and decomposable input attributions.
DARPA ’s explainable artificial intelligence ( XAI ) program
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Pathwise Explanation of ReLU Neural Networks
A new explanation method for ReLU neural networks that builds piecewise linear models from selected connected subsets of hidden units, called paths, to produce adjustable and decomposable input attributions.