A neural network trained with an extra checksum output can flag out-of-distribution predictions by measuring how strongly its own outputs violate the checksum relation.
Fundamental concepts and terminology,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Soft Checksums to Flag Untrustworthy Machine Learning Surrogate Predictions and Application to Atomic Physics Simulations
A neural network trained with an extra checksum output can flag out-of-distribution predictions by measuring how strongly its own outputs violate the checksum relation.