testRNN is the first coverage-guided testing tool for LSTMs that uses mutation-based test generation and three novel structural coverage metrics to evaluate network robustness.
DeepGauge: Comprehensive and multi-granularity testing criteria for gauging the robustness of deep learning systems,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
testRNN: Coverage-guided Testing on Recurrent Neural Networks
testRNN is the first coverage-guided testing tool for LSTMs that uses mutation-based test generation and three novel structural coverage metrics to evaluate network robustness.