CRITS is an intrinsically interpretable time series classifier whose local saliency maps are the exact per-sample weights of the model, obtained without gradients, perturbations, or upsampling.
In: Advances in Knowledge Discovery and Data Mining: 23rd Pacific-Asia Conference, PAKDD 2019, Macau, China, April 14-17
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
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
CRITS: Convolutional Rectifier for Interpretable Time Series Classification
CRITS is an intrinsically interpretable time series classifier whose local saliency maps are the exact per-sample weights of the model, obtained without gradients, perturbations, or upsampling.