InceptionTime: Finding AlexNet for time series classification
Open accessThe DOI matches its Crossref record; 38 of the 39 references it cites were found in a registry or an index.
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“where multi-scale convolutional layer and convolution of length 1 enable model to extract rich high-dimensional features with limited parameters.”
From IENet: a robust convolutional neural network for EEG based brain-computer interfaces (2022) · cites this paper as [62]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“By applying convolutions of different lengths in the convolutional layer, IENet is capable of generating the long-term and short-term features of EEG simultaneously to improve feature diversity [19, 62].”
From IENet: a robust convolutional neural network for EEG based brain-computer interfaces (2022) · cites this paper as [62]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The FdrConv1 can reduce the number of model parameters and avoid overfitting.”
From IENet: a robust convolutional neural network for EEG based brain-computer interfaces (2022) · cites this paper as [62]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Moreover, 1D time series deep learning has emerged and they provide better accuracies than conventional ML algorithms and are even much faster like [99].”
From Wearable sensors and machine learning in post-stroke rehabilitation assessment: A systematic review (2022) · cites this paper as [99]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Therefore, we apply the ensemble of three IE models instead of a single one to improve stability [62].”
From IENet: a robust convolutional neural network for EEG based brain-computer interfaces (2022) · cites this paper as [62]
3 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 2×
“Each residual block’s input is transferred via a shortcut linear connection to be added to the next block’s input, thus mitigating the vanishing gradient problem by allowing a direct flow of the gradient (He et al., 2016).”
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.11231 · Cited by 4,636 · cited 7×
“In contrast to networks designed for images, we are able to explore filters 10 times longer than recent Inception variants for image recognition tasks (Szegedy et al., 2017).”
BackgroundInfluentialA Comparison of Alternative Tests of Significance for the Problem of $m$ Rankings
Friedman, M. (1940) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177731944 · Cited by 2,785 · cited 1×
“Following the recommendations in Demšar (2006) we adopted the Friedman test (Friedman, 1940) in order to reject the null hypothesis.”
MethodTime series classification from scratch with deep neural networks: A strong baseline
Wang, Z., Yan, W., & Oates, T. (2017) · 2017 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2017.7966039 · Cited by 2,299 · cited 5×
“…of deep learning techniques in supervised learning such as image recognition (Zhang et al., 2018) and natural language processing (Guan et al., 2019), researchers started investigating these complex machine learning models for TSC (Wang et al., 2017; Cui et al., 2016; Ismail Fawaz et al., 2019a).”
InfluentialBagnall, A., Lines, J., Bostrom, A., Large, J., & Keogh, E. (2017) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-016-0483-9 · Cited by 1,377 · cited 10×
“5 illustrates the critical difference diagram with InceptionTime added to the mix of the current state-of-the-art classifiers for time series data, whose results were taken from Bagnall et al. (2017).”
BackgroundMethodResultInfluentialDerivative Dynamic Time Warping
Keogh, E. J., & Pazzani, M. J. (2001) · Proceedings of the 2001 SIAM International Conference on Data Mining · doi:10.1137/1.9781611972719.1 · Cited by 1,143 · cited 1×
“Much research has subsequently focused on finding alternative similarity measures (Marteau 2009; Stefan et al. 2013; Keogh and Pazzani 2001; Vlachos et al. 2006), however none have been found to significantly outperform NN-DTW on the UCR Archive (Lines and Bagnall 2015).”
Background
Research works printed but not linked: 14
- Benavoli A, Corani G, Mangili F (2016) Should we really use post-hoc tests based on mean-ranks? Machine Learning Research 17(1):152-161
- Cui Z, Chen W, Chen Y (2016) Multi-scale convolutional neural networks for time series classification. ArXiv 1603.06995 · arXiv
- Cuturi M, Blondel M (2017) Soft-dtw: a differentiable loss function for time-series. In: International Conference on Machine Learnin, pp 894-903
- Demšar J (2006) Statistical comparisons of classifiers over multiple data sets. Mach Learn Res 7:1–30
- Garcia S, Herrera F (2008) An extension on 'statistical comparisons of classifiers over multiple data sets' for all pairwise comparisons. Machine learning research 9:2677-2694
- Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: International Conference on Artificial Intelligence and Statistics, vol 9, pp 249-256
- Guan C, Wang X, Zhang Q, Chen R, He D, Xie X (2019) Towards a deep and unified understanding of deep neural models in NLP. In: International Conference on Machine Learning, pp 2454-2463
- Ismail Fawaz H, Forestier G, Weber J, Idoumghar L, Muller PA (2019b) Deep learning for time series classification: a review. Data Mining and Knowledge Discovery · DOI · Paper page
- Kingma DP, Ba J (2015) Adam: A method for stochastic optimization. In: International Conference on Learning Representations
- Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet Classification with Deep Convolutional Neural Networks. In: Advances in Neural Information Processing Systems, pp 1097-1105
- Le Guennec A, Malinowski S, Tavenard R (2016) Data augmentation for time series classification using convolutional neural networks. In: ECML/PKDD Workshop on Advanced Analytics and Learning on Temporal Data
- Luo W, Li Y, Urtasun R, Zemel R (2016) Understanding the effective receptive field in deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp 48984906
- Pelletier C, Webb GI, Petitjean F (2019) Temporal convolutional neural network for the classification of satellite image time series. Remote Sensing 11(5):523 · DOI
- Sabour S, Frosst N, Hinton GE (2017) Dynamic routing between capsules. In: Advances in Neural Information Processing Systems, pp 3856-3866
Cited by
A Transformer-based Framework for Multivariate Time Series Representation Learning
Zerveas, G., Jayaraman, S., Patel, D., Bhamidipaty, A., & Eickhoff, C. (2021) · Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining · doi:10.1145/3447548.3467401 · Cited by 1,278
“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 architectures such as In…”
BackgroundMethodInfluentialDempster, A., Petitjean, F., & Webb, G. I. (2020) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-020-00701-z · Cited by 982
Self-citationTheissler, A., Pérez-Velázquez, J., Kettelgerdes, M., & Elger, G. (2021) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2021.107864 · Cited by 581
Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL
Strodthoff, N., Wagner, P., Schaeffter, T., & Samek, W. (2021) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2020.3022989 · Cited by 491
MiniRocket: A Very Fast (Almost) Deterministic Transform for Time Series Classification
Dempster, A., Schmidt, D. F., & Webb, G. I. (2021) · Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining · doi:10.1145/3447548.3467231 · Cited by 490
“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].”
MethodSelf-citation
Metadata
- Authors
- Ismail Fawaz, H., Lucas, B., Forestier, G., Pelletier, C., Schmidt, D. F., Weber, J., Webb, G. I., Idoumghar, L., Muller, P.-A., & Petitjean, F.
- Affiliations
- Monash University (AU)
- Université de Haute-Alsace (FR)
- Centre National de la Recherche Scientifique (FR)
- ORCID
- Venue
- Data Mining and Knowledge Discovery
- Published
- 2020-09-07
- Volume
- 34
- Issue
- 6
- Pages
- 1936-1962
- ISSN
- 1384-5810 (ISSN-L)
- 1573-756X
- OpenAlex
- W2972810968
- Cited by
- 1,788
- References
- 39
- Citations by year
- 2026: 397 · 2025: 435 · 2024: 334 · 2023: 280 · 2022: 194 · 2021: 114 · 2020: 32
- FWCI
- 84.00
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- www.springer.com/tdm (tdm)
- www.springer.com/tdm (vor)
- Locations
- Data Mining and Knowledge Discovery (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- HAL (submittedVersion, other-oa)
- HAL Portal Artxiker (Hindustan Aeronautics Limited (India)) (submittedVersion)
- univOAK (4 institutions : Université de Strasbourg, Université de Haute Alsace, INSA Strasbourg, Bibliothèque Nationale et Universitaire de Strasbourg) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Agence Nationale de la Recherche (ANR-17-CE23-0015)
- Topics
- Physical Sciences › Computer Science › Signal Processing › Time Series Analysis and Forecasting
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- time series classification, InceptionTime, Inception-v4, ensemble convolutional neural networks, deep learning, scalability, training time complexity, AlexNet
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: InceptionTime: Finding AlexNet for time series classification. https://app.cochat.ai/papers/10.1007/s10618-020-00710-y
- The paper
- Ismail Fawaz, H., Lucas, B., Forestier, G., Pelletier, C., Schmidt, D. F., Weber, J., Webb, G. I., Idoumghar, L., Muller, P.-A., & Petitjean, F. (2020). InceptionTime: Finding AlexNet for time series classification. Data Mining and Knowledge Discovery. https://doi.org/10.1007/s10618-020-00710-y
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.