TSViz: Demystification of Deep Learning Models for Time-Series Analysis
This paper presents a novel framework for the demystification of convolutional deep learning models for time-series analysis. This is a step toward making informed/explainable decisions in the domain of time series, powered by deep learning. There have been numerous efforts to increase the interpret...
Автори: | Shoaib Ahmed Siddiqui, Dominique Mercier, Mohsin Munir, Andreas Dengel, Sheraz Ahmed |
---|---|
Формат: | Стаття |
Мова: | English |
Опубліковано: |
IEEE
2019-01-01
|
Серія: | IEEE Access |
Предмети: | |
Онлайн доступ: | https://ieeexplore.ieee.org/document/8695734/ |
Схожі ресурси
Схожі ресурси
-
TSInsight: A Local-Global Attribution Framework for Interpretability in Time Series Data
за авторством: Shoaib Ahmed Siddiqui, та інші
Опубліковано: (2021-11-01) -
TimeREISE: Time Series Randomized Evolving Input Sample Explanation
за авторством: Dominique Mercier, та інші
Опубліковано: (2022-05-01) -
Linear Model and Gradient Feature Elimination Algorithm Based on Seasonal Decomposition for Time Series Forecasting
за авторством: Sheng-Tzong Cheng, та інші
Опубліковано: (2025-03-01) -
DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series
за авторством: Mohsin Munir, та інші
Опубліковано: (2019-01-01) -
Random Noise vs. State-of-the-Art Probabilistic Forecasting Methods: A Case Study on CRPS-Sum Discrimination Ability
за авторством: Alireza Koochali, та інші
Опубліковано: (2022-05-01)