Prophecy infers formal properties of feed-forward neural networks by extracting rules from neuron activation patterns that imply desirable output behaviors.
https://keras.io/api/datasets/cifar10/, [Accessed 31-01-2025]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Prophecy: Inferring Formal Properties from Neuron Activations
Prophecy infers formal properties of feed-forward neural networks by extracting rules from neuron activation patterns that imply desirable output behaviors.