TSViz: Demystification of Deep Learning Models for Time-Series Analysis

Abstract

This paper presents a novel framework for demystification of convolutional deep learning models for time-series analysis. This is a step towards making informed/explainable decisions in the domain of time-series, powered by deep learning. There have been numerous efforts to increase the interpretability of image-centric deep neural network models, where the learned features are more intuitive to visualize. Visualization in time-series domain is much more complicated as there is no direct interpretation of the filters and inputs as compared to the image modality. In addition, little or no concentration has been devoted for the development of such tools in the domain of time-series in the past. TSViz provides possibilities to explore and analyze a network from different dimensions at different levels of abstraction which includes identification of parts of the input that were responsible for a prediction (including per filter saliency), importance of different filters present in the network for a particular prediction, notion of diversity present in the network through filter clustering, understanding of the main sources of variation learnt by the network through inverse optimization, and analysis of the network's robustness against adversarial noise. As a sanity check for the computed influence values, we demonstrate results regarding pruning of neural networks based on the computed influence information. These representations allow to understand the network features so that the acceptability of deep networks for time-series data can be enhanced. This is extremely important in domains like finance, industry 4.0, self-driving cars, health-care, counter-terrorism etc., where reasons for reaching a particular prediction are equally important as the prediction itself. We assess the proposed framework for interpretability with a set of desirable properties essential for any method.

arXiv comment7 Pages (6 + 1 for references), 7 figures

References in corpus (12)

• Explaining and Harnessing Adversarial Examples
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• Methods for Interpreting and Understanding Deep Neural Networks
• Learning Important Features Through Propagating Activation Differences
• Understanding Neural Networks Through Deep Visualization
• Understanding Black-box Predictions via Influence Functions
• Predicting Parameters in Deep Learning
• Understanding Neural Networks through Representation Erasure
• Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
• Towards Robust Interpretability with Self-Explaining Neural Networks
• Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car
• Faster gaze prediction with dense networks and Fisher pruning

Cited by in corpus (19)

• Time Series Forecasting With Deep Learning: A Survey
• Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Direction
• Deep Learning for Time Series Forecasting: A Survey
• Explainable Artificial Intelligence (XAI) on TimeSeries Data: A Survey
• Explaining Time Series Predictions with Dynamic Masks
• Privacy Meets Explainability: A Comprehensive Impact Benchmark
• Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Features
• TSXplain: Demystification of DNN Decisions for Time-Series using Natural Language and Statistical Features
• Sequential Interpretability: Methods, Applications, and Future Direction for Understanding Deep Learning Models in the Context of Sequential Data
• What went wrong and when? Instance-wise Feature Importance for Time-series Models
• Explaining Deep Learning Models for Structured Data using Layer-Wise Relevance Propagation
• Towards an Awareness of Time Series Anomaly Detection Models' Adversarial Vulnerability
• PatchX: Explaining Deep Models by Intelligible Pattern Patches for Time-series Classification
• TSInsight: A local-global attribution framework for interpretability in time-series data
• CAFO: Feature-Centric Explanation on Time Series Classification
• Interpreting Deep Models through the Lens of Data
• Benchmarking adversarial attacks and defenses for time-series data
• P2ExNet: Patch-based Prototype Explanation Network
• FREQuency ATTribution: benchmarking frequency-based occlusion for time series data