Abstraction-refinement over neuron merging computes provably sufficient and minimal explanations of neural network predictions substantially faster than verifying on the full network.
Choice of Activation Function In our main experiments, we used networks with either ReLU or sigmoid activation, respectively (Sec
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
-
Explaining, Fast and Slow: Abstraction and Refinement of Provable Explanations
Abstraction-refinement over neuron merging computes provably sufficient and minimal explanations of neural network predictions substantially faster than verifying on the full network.