Time Series Model Attribution Visualizations as Explanations

09/27/2021
by   Udo Schlegel, et al.
0

Attributions are a common local explanation technique for deep learning models on single samples as they are easily extractable and demonstrate the relevance of input values. In many cases, heatmaps visualize such attributions for samples, for instance, on images. However, heatmaps are not always the ideal visualization to explain certain model decisions for other data types. In this review, we focus on attribution visualizations for time series. We collect attribution heatmap visualizations and some alternatives, discuss the advantages as well as disadvantages and give a short position towards future opportunities for attributions and explanations for time series.

READ FULL TEXT
research
12/08/2020

An Empirical Study of Explainable AI Techniques on Deep Learning Models For Time Series Tasks

Decision explanations of machine learning black-box models are often gen...
research
04/06/2020

TSInsight: A local-global attribution framework for interpretability in time-series data

With the rise in the employment of deep learning methods in safety-criti...
research
08/10/2022

TSInterpret: A unified framework for time series interpretability

With the increasing application of deep learning algorithms to time seri...
research
02/06/2023

Importance attribution in neural networks by means of persistence landscapes of time series

We propose and implement a method to analyze time series with a neural n...
research
02/06/2019

Global Explanations of Neural Networks: Mapping the Landscape of Predictions

A barrier to the wider adoption of neural networks is their lack of inte...
research
11/08/2018

Looking Deeper into Deep Learning Model: Attribution-based Explanations of TextCNN

Layer-wise Relevance Propagation (LRP) and saliency maps have been recen...
research
06/11/2023

Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization

Feature visualization has gained substantial popularity, particularly af...

Please sign up or login with your details

Forgot password? Click here to reset