PatchX: Explaining Deep Models by Intelligible Pattern Patches for Time-series Classification

Abstract

The classification of time-series data is pivotal for streaming data and comes with many challenges. Although the amount of publicly available datasets increases rapidly, deep neural models are only exploited in a few areas. Traditional methods are still used very often compared to deep neural models. These methods get preferred in safety-critical, financial, or medical fields because of their interpretable results. However, their performance and scale-ability are limited, and finding suitable explanations for time-series classification tasks is challenging due to the concepts hidden in the numerical time-series data. Visualizing complete time-series results in a cognitive overload concerning our perception and leads to confusion. Therefore, we believe that patch-wise processing of the data results in a more interpretable representation. We propose a novel hybrid approach that utilizes deep neural networks and traditional machine learning algorithms to introduce an interpretable and scale-able time-series classification approach. Our method first performs a fine-grained classification for the patches followed by sample level classification.

arXiv comment8 pages, 8 figures, 6 tables, submitted to IJCNN 2021

References in corpus (9)

• Natural Language Processing (almost) from Scratch
• Towards Robust Interpretability with Self-Explaining Neural Networks
• Deep Learning for Time-Series Analysis
• TSViz: Demystification of Deep Learning Models for Time-Series Analysis
• Explaining Deep Classification of Time-Series Data with Learned Prototypes
• TSInsight: A local-global attribution framework for interpretability in time-series data
• Interpreting Deep Models through the Lens of Data
• Explaining Regression Based Neural Network Model
• P2ExNet: Patch-based Prototype Explanation Network