# TimeNet: Pre-trained deep recurrent neural network for time series classification

arXiv: https://arxiv.org/abs/1706.08838 · HTML: https://mlsanity.com/paper/1706.08838/

## Key facts

- Cited by 46 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jun 2017.

## Built on by (most cited first, 30 of 46)

- [TS2Vec: Towards Universal Representation of Time Series](https://mlsanity.com/paper/2106.10466/) (2021)
- [Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding](https://mlsanity.com/paper/2106.00750/) (2021)
- [Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects](https://mlsanity.com/paper/2306.10125/) (2023)
- [Unsupervised Time-Series Representation Learning with Iterative Bilinear Temporal-Spectral Fusion](https://mlsanity.com/paper/2202.04770/) (2022)
- [Chaos as an interpretable benchmark for forecasting and data-driven modelling](https://mlsanity.com/paper/2110.05266/) (2021)
- [Deep Learning for Time Series Classification and Extrinsic Regression: A Current Survey](https://mlsanity.com/paper/2302.02515/) (2023)
- [A Survey on Time-Series Pre-Trained Models](https://mlsanity.com/paper/2305.10716/) (2023)
- [TimesURL: Self-supervised Contrastive Learning for Universal Time Series Representation Learning](https://mlsanity.com/paper/2312.15709/) (2023)
- [TimeMAE: Self-Supervised Representations of Time Series with Decoupled Masked Autoencoders](https://mlsanity.com/paper/2303.00320/) (2023)
- [Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency](https://mlsanity.com/paper/2306.02109/) (2023)
- [MHCCL: Masked Hierarchical Cluster-Wise Contrastive Learning for Multivariate Time Series](https://mlsanity.com/paper/2212.01141/) (2022)
- [A comparison of LSTM and GRU networks for learning symbolic sequences](https://mlsanity.com/paper/2107.02248/) (2021)
- [T-Rep: Representation Learning for Time Series using Time-Embeddings](https://mlsanity.com/paper/2310.04486/) (2023)
- [CARLA: Self-supervised Contrastive Representation Learning for Time Series Anomaly Detection](https://mlsanity.com/paper/2308.09296/) (2023)
- [Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensions](https://mlsanity.com/paper/2203.06852/) (2022)
- [Unsupervised Representation Learning for Time Series: A Review](https://mlsanity.com/paper/2308.01578/) (2023)
- [Self-Supervised Learning of Time Series Representation via Diffusion Process and Imputation-Interpolation-Forecasting Mask](https://mlsanity.com/paper/2405.05959/) (2024)
- [Unsupervised pre-training of graph transformers on patient population graphs](https://mlsanity.com/paper/2207.10603/) (2022)
- [Efficient High-Resolution Time Series Classification via Attention Kronecker Decomposition](https://mlsanity.com/paper/2403.04882/) (2024)
- [EMIT- Event-Based Masked Auto Encoding for Irregular Time Series](https://mlsanity.com/paper/2409.16554/) (2024)
- [Computer Vision Self-supervised Learning Methods on Time Series](https://mlsanity.com/paper/2109.00783/) (2021)
- [FakeTransformer: Exposing Face Forgery From Spatial-Temporal Representation Modeled By Facial Pixel Variations](https://mlsanity.com/paper/2111.07601/) (2021)
- [Face Forgery Detection Based on Facial Region Displacement Trajectory Series](https://mlsanity.com/paper/2212.03678/) (2022)
- [Forecasting Market Prices using DL with Data Augmentation and Meta-learning: ARIMA still wins!](https://mlsanity.com/paper/2110.10233/) (2021)
- [Self-Distilled Representation Learning for Time Series](https://mlsanity.com/paper/2311.11335/) (2023)
- [SeqFusion: Sequential Fusion of Pre-Trained Models for Zero-Shot Time-Series Forecasting](https://mlsanity.com/paper/2503.02836/) (2025)
- [A Self-Supervised Framework for Function Learning and Extrapolation](https://mlsanity.com/paper/2106.07369/) (2021)
- [Spectral Propagation Graph Network for Few-shot Time Series Classification](https://mlsanity.com/paper/2202.04769/) (2022)
- [Anamnesic Neural Differential Equations with Orthogonal Polynomial Projections](https://mlsanity.com/paper/2303.01841/) (2023)
- [Aircraft Trajectory Segmentation-based Contrastive Coding: A Framework for Self-supervised Trajectory Representation](https://mlsanity.com/paper/2407.20028/) (2024)

## Abstract (arXiv)

Inspired by the tremendous success of deep Convolutional Neural Networks as generic feature extractors for images, we propose TimeNet: a deep recurrent neural network (RNN) trained on diverse time series in an unsupervised manner using sequence to sequence (seq2seq) models to extract features from time series. Rather than relying on data from the problem domain, TimeNet attempts to generalize time series representation across domains by ingesting time series from several domains simultaneously. Once trained, TimeNet can be used as a generic off-the-shelf feature extractor for time series. The representations or embeddings given by a pre-trained TimeNet are found to be useful for time series classification (TSC). For several publicly available datasets from UCR TSC Archive and an industrial telematics sensor data from vehicles, we observe that a classifier learned over the TimeNet embeddings yields significantly better performance compared to (i) a classifier learned over the embeddings given by a domain-specific RNN, as well as (ii) a nearest neighbor classifier based on Dynamic Time Warping.