The paper proposes treating classifier scores as a time-like axis and fitting survival-analysis hazard models to produce global and score-dependent local explanations for time series classification.
Principles of explanatory debugging to personalize interactive machine learning
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Local Score Dependent Model Explanation for Time Dependent Covariates
The paper proposes treating classifier scores as a time-like axis and fitting survival-analysis hazard models to produce global and score-dependent local explanations for time series classification.