Encoding time-series explanations through self-supervised model behavior consistency
Interpreting time series models is uniquely challenging because it requires identifying both
the location of time series signals that drive model predictions and their matching to an …
the location of time series signals that drive model predictions and their matching to an …
Time-series Shapelets with Learnable Lengths
A Yamaguchi, K Ueno, H Kashima - Proceedings of the 32nd ACM …, 2023 - dl.acm.org
Shapelets are subsequences that are effective for classifying time-series instances.
Learning shapelets by a continuous optimization has recently been studied to improve …
Learning shapelets by a continuous optimization has recently been studied to improve …
Toward Learning Model-Agnostic Explanations for Deep Learning-Based Signal Modulation Classifiers
Y Tian, D Xu, E Tong, R Sun, K Chen… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Recent advances in deep learning (DL) have brought tremendous gains in signal
modulation classification. However, DL-based classifiers lack transparency and …
modulation classification. However, DL-based classifiers lack transparency and …
Learning Counterfactual Explanations with Intervals for Time-series Classification
A Yamaguchi, K Ueno, R Shingaki… - Proceedings of the 33rd …, 2024 - dl.acm.org
The need for explainability in time-series classification models has been increasing.
Counterfactual explanations recommend how to modify the features of an original instance …
Counterfactual explanations recommend how to modify the features of an original instance …
A Survey of Explainable Artificial Intelligence (XAI) in Financial Time Series Forecasting
PD Arsenault, S Wang, JM Patenande - arXiv preprint arXiv:2407.15909, 2024 - arxiv.org
Artificial Intelligence (AI) models have reached a very significant level of accuracy. While
their superior performance offers considerable benefits, their inherent complexity often …
their superior performance offers considerable benefits, their inherent complexity often …
Explaining deep multi-class time series classifiers
Explainability helps users trust deep learning solutions for time series classification.
However, existing explainability methods for multi-class time series classifiers focus on one …
However, existing explainability methods for multi-class time series classifiers focus on one …