InceptionTime: Finding AlexNet for time series classification

By Hassan Ismail Fawaz, Benjamin Lucas, Germain Forestier, Charlotte Pelletier, Daniel F. Schmidt, Jonathan Weber, Geoffrey I. Webb, Lhassane Idoumghar, Pierre-Alain Muller, Franccois Petitjean. Data mining and knowledge discovery, 2019

1,670 citations recorded by the source corpus.

This paper brings deep learning at the forefront of research into time series classification (TSC). TSC is the area of machine learning tasked with the categorization (or labelling) of time series. The last few decades of work in this area have led to significant progress in the accuracy of classifiers, with the state of the art now represented by the HIVE-COTE algorithm. While extremely accurate, HIVE-COTE cannot be applied to many real-world datasets because of its high training time complexity in O(N2·T4)\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$O(N^2\cdot T^4)$$\end{document} for a dataset with N time series of length T. For example, it takes HIVE-COTE more than 8 days to learn from a small dataset with N=1500\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$N=1500$$\end{document} time series of short length T=46\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$T=46$$\end{document}. Meanwhile deep learning has received enormous attention because of its high accuracy and scalability. Recent approaches to deep learning for TSC have been scalable, but less accurate than HIVE-COTE. We introduce InceptionTime—an ensemble of deep Convolutional Neural Network models, inspired by the Inception-v4 architecture. Our experiments show that InceptionTime is on par with HIVE-COTE in terms of accuracy while being much more scalable: not only can it learn from 1500 time series in one hour but it can also learn from 8M time series in 13 h, a quantity of data that is fully out of reach of HIVE-COTE.

Subfields: Artificial Intelligence, Management Science and Operations Research, Signal Processing

View Paper: https://www.semanticscholar.org/paper/0ddd01d67b0056cadc0845e0e020fee944afa916

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

In Signal Processing

Citations in the corpus

MiniRocket: A Very Fast (Almost) Deterministic Transform for Time Series Classification (2020, methodology): “According to [2, 28, 27], the most accurate current methods for time series classification are HIVE-COTE and its variants [22], TS-CHIEF [36], InceptionTime [16], and Rocket [8].”
A Transformer-based Framework for Multivariate Time Series Representation Learning (2020, methodology): “Regression and classification of time series: Currently, nondeep learning methods such as TS-CHIEF [29], HIVE-COTE [21], and ROCKET [8, 9] constitute the state of the art for time series regression and classification based on evaluations on public benchmarks [2, 30], followed by CNN-based deep archi”
Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals (2021, methodology): “For example, some 1D-CNN models [51], [52] have been proposed to solve time series tasks with a very simple structure and the sota performance.”