Evaluation Of Post-hoc Interpretability Methods In Time-series Classification

Time-series data is becoming increasingly available and there is a need for automated analysis tools that can extract interpretable and actionable knowledge from them. Artificial intelligence (AI) technologies and neural networks are opening the path towards highly accurate predictive tools for time-series regression and classification learning tasks. However, the adoption of AI technologies as black-box tools is problematic in several applied contexts. To address this, interpretable AI approaches are being developed to provide more transparency and explainability in the decision-making process.