Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey
arXiv:2104.00950
Abstract
Most of state of the art methods applied on time series consist of deep learning methods that are too complex to be interpreted. This lack of interpretability is a major drawback, as several applications in the real world are critical tasks, such as the medical field or the autonomous driving field. The explainability of models applied on time series has not gather much attention compared to the computer vision or the natural language processing fields. In this paper, we present an overview of existing explainable AI (XAI) methods applied on time series and illustrate the type of explanations they produce. We also provide a reflection on the impact of these explanation methods to provide confidence and trust in the AI systems.
References in corpus (16)
- LSTM Fully Convolutional Networks for Time Series Classification
- What Does Explainable AI Really Mean? A New Conceptualization of Perspectives
- TSViz: Demystification of Deep Learning Models for Time-Series Analysis
- The UEA multivariate time series classification archive, 2018
- Clinical Intervention Prediction and Understanding using Deep Networks
- Counterfactual Explanations for Machine Learning on Multivariate Time Series Data
- Explainability and Adversarial Robustness for RNNs
- Explaining Deep Classification of Time-Series Data with Learned Prototypes
- Fooling a Real Car with Adversarial Traffic Signs
- Interpreting Deep Classifier by Visual Distillation of Dark Knowledge
- Learning Interpretable Shapelets for Time Series Classification through Adversarial Regularization
- Interpretation of Deep Temporal Representations by Selective Visualization of Internally Activated Nodes
- Generalised Interpretable Shapelets for Irregular Time Series
- Attention Mechanism for Multivariate Time Series Recurrent Model Interpretability Applied to the Ironmaking Industry
- Series Saliency: Temporal Interpretation for Multivariate Time Series Forecasting
- TSInsight: A local-global attribution framework for interpretability in time-series data
Cited by in corpus (5)
- Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions
- Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction
- Toward Explainable AI for Regression Models
- The Thousand Faces of Explainable AI Along the Machine Learning Life Cycle: Industrial Reality and Current State of Research
- A Semi-Automated Solution Approach Recommender for a Given Use Case: a Case Study for AI/ML in Oncology via Scopus and OpenAI