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

02/08/2018
by   Shoaib Ahmed Siddiqui, et al.
0

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 is much more complicated as there is no direct interpretation of the filters and inputs as compared to 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. The visualization engine of the presented framework provides possibilities to explore and analyze a network from different dimensions at four different levels of abstraction. This enables the user to uncover different aspects of the model which includes important filters, filter clusters, and input saliency maps. 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. The framework [Framework download link: https://hidden.for.blind.review] can also aid in discovery of the filters which are contributing nothing to the final prediction, hence, can be pruned without any significant loss in performance.

READ FULL TEXT

page 5

page 6

research
03/14/2022

Don't Get Me Wrong: How to apply Deep Visual Interpretations to Time Series

The correct interpretation and understanding of deep learning models is ...
research
12/16/2020

Series Saliency: Temporal Interpretation for Multivariate Time Series Forecasting

Time series forecasting is an important yet challenging task. Though dee...
research
08/11/2021

Towards data-driven filters in Paraview

Recent progress in scientific visualization has expanded the scope of vi...
research
06/23/2018

Multilevel Wavelet Decomposition Network for Interpretable Time Series Analysis

Recent years have witnessed the unprecedented rising of time series from...
research
08/18/2021

XAI Methods for Neural Time Series Classification: A Brief Review

Deep learning models have recently demonstrated remarkable results in a ...
research
03/12/2021

Visualising Deep Network's Time-Series Representations

Despite the popularisation of the machine learning models, more often th...
research
07/27/2023

Explainable Techniques for Analyzing Flow Cytometry Cell Transformers

Explainability for Deep Learning Models is especially important for clin...

Please sign up or login with your details

Forgot password? Click here to reset