# Deep learning for time series classification

arXiv: https://arxiv.org/abs/2010.00567 · HTML: https://mlsanity.com/paper/2010.00567/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Oct 2020.

## Built on by (most cited first, 15 of 15)

- [Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey](https://mlsanity.com/paper/2302.02515/) (2023)
- [Universal Time-Series Representation Learning: A Survey](https://mlsanity.com/paper/2401.03717/) (2024)
- [dCAM: Dimension-wise Class Activation Map for Explaining Multivariate Data Series Classification](https://mlsanity.com/paper/2207.12165/) (2022)
- [MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series](https://mlsanity.com/paper/2509.25278/) (2025)
- [Fast and Robust Video-Based Exercise Classification via Body Pose Tracking and Scalable Multivariate Time Series Classifiers](https://mlsanity.com/paper/2210.00507/) (2022)
- [Appliance Detection Using Very Low-Frequency Smart Meter Time Series](https://mlsanity.com/paper/2305.10352/) (2023)
- [Robust and Explainable Detector of Time Series Anomaly via Augmenting Multiclass Pseudo-Anomalies](https://mlsanity.com/paper/2505.20765/) (2025)
- [Surface Similarity Parameter: A New Machine Learning Loss Metric for Oscillatory Spatio-Temporal Data](https://mlsanity.com/paper/2204.06843/) (2022)
- [Moving Beyond Functional Connectivity: Time-Series Modeling for fMRI-Based Brain Disorder Classification](https://mlsanity.com/paper/2602.08262/) (2026)
- [A Foundation Model for Instruction-Conditioned In-Context Time Series Tasks](https://mlsanity.com/paper/2603.22586/) (2026)
- [DK-Root: A Joint Data-and-Knowledge-Driven Framework for Root Cause Analysis of QoE Degradations in Mobile Networks](https://mlsanity.com/paper/2511.11737/) (2025)
- [UMSNet: An Universal Multi-sensor Network for Human Activity Recognition](https://mlsanity.com/paper/2205.11756/) (2022)
- [Deep Learning Architectures for FSCV, a Comparison](https://mlsanity.com/paper/2212.01960/) (2022)
- [MoSSDA: A Semi-Supervised Domain Adaptation Framework for Multivariate Time-Series Classification using Momentum Encoder](https://mlsanity.com/paper/2508.08280/) (2025)
- [Label-Efficient Time Series Classification at Scale: A Dual-Stream OSSE-LSTM with Counterfactual Attribution](https://mlsanity.com/paper/2610.02704/) (2026)

## Abstract (arXiv)

Time series analysis is a field of data science which is interested in analyzing sequences of numerical values ordered in time. Time series are particularly interesting because they allow us to visualize and understand the evolution of a process over time. Their analysis can reveal trends, relationships and similarities across the data. There exists numerous fields containing data in the form of time series: health care (electrocardiogram, blood sugar, etc.), activity recognition, remote sensing, finance (stock market price), industry (sensors), etc. Time series classification consists of constructing algorithms dedicated to automatically label time series data. The sequential aspect of time series data requires the development of algorithms that are able to harness this temporal property, thus making the existing off-the-shelf machine learning models for traditional tabular data suboptimal for solving the underlying task. In this context, deep learning has emerged in recent years as one of the most effective methods for tackling the supervised classification task, particularly in the field of computer vision. The main objective of this thesis was to study and develop deep neural networks specifically constructed for the classification of time series data. We thus carried out the first large scale experimental study allowing us to compare the existing deep methods and to position them compared other non-deep learning based state-of-the-art methods. Subsequently, we made numerous contributions in this area, notably in the context of transfer learning, data augmentation, ensembling and adversarial attacks. Finally, we have also proposed a novel architecture, based on the famous Inception network (Google), which ranks among the most efficient to date.