Explainable AI for time series classification: a review, taxonomy and research directions
Time series data is increasingly used in a wide range of fields, and it is often relied on in
crucial applications and high-stakes decision-making. For instance, sensors generate time …
crucial applications and high-stakes decision-making. For instance, sensors generate time …
Generative time series forecasting with diffusion, denoise, and disentanglement
Time series forecasting has been a widely explored task of great importance in many
applications. However, it is common that real-world time series data are recorded in a short …
applications. However, it is common that real-world time series data are recorded in a short …
Benchmarking deep learning interpretability in time series predictions
Saliency methods are used extensively to highlight the importance of input features in model
predictions. These methods are mostly used in vision and language tasks, and their …
predictions. These methods are mostly used in vision and language tasks, and their …
Improving deep learning interpretability by saliency guided training
AA Ismail, H Corrada Bravo… - Advances in Neural …, 2021 - proceedings.neurips.cc
Saliency methods have been widely used to highlight important input features in model
predictions. Most existing methods use backpropagation on a modified gradient function to …
predictions. Most existing methods use backpropagation on a modified gradient function to …
Temporal quality degradation in AI models
As AI models continue to advance into many real-life applications, their ability to maintain
reliable quality over time becomes increasingly important. The principal challenge in this …
reliable quality over time becomes increasingly important. The principal challenge in this …
Learning to evaluate perception models using planner-centric metrics
Variants of accuracy and precision are the gold-standard by which the computer vision
community measures progress of perception algorithms. One reason for the ubiquity of these …
community measures progress of perception algorithms. One reason for the ubiquity of these …
Better Understanding of the Metamorphosis of Pregnancy (BUMP): protocol for a digital feasibility study in women from preconception to postpartum
SM Goodday, E Karlin, A Brooks, C Chapman… - NPJ Digital …, 2022 - nature.com
Abstract The Better Understanding the Metamorphosis of Pregnancy (BUMP) study is a
longitudinal feasibility study aimed to gain a deeper understanding of the pre-pregnancy …
longitudinal feasibility study aimed to gain a deeper understanding of the pre-pregnancy …
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 …
Learning perturbations to explain time series predictions
J Enguehard - International Conference on Machine …, 2023 - proceedings.mlr.press
Explaining predictions based on multivariate time series data carries the additional difficulty
of handling not only multiple features, but also time dependencies. It matters not only what …
of handling not only multiple features, but also time dependencies. It matters not only what …
Limesegment: Meaningful, realistic time series explanations
Abstract LIME (Locally Interpretable Model-Agnostic Explanations) has become a popular
way of generating explanations for tabular, image and natural language models, providing …
way of generating explanations for tabular, image and natural language models, providing …