A deep multi-task representation learning method for time series classification and retrieval

DOI10.1016/J.INS.2020.12.062MaRDI QIDQ2124168zbMATH OpenOpenAlexFDO

Authors Yanyan Li

Publication date 14 April 2022

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ins.2020.12.062

zbMATH Keywords

multi-task learningrepresentation learningtime series classificationtime series retrieval

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Artificial neural networks and deep learning (68T07)

Recommendations

• End-to-end deep representation learning for time series clustering: a comparative study
• Learning a symbolic representation for multivariate time series classification
• Deep learning for time series classification: a review
• The great multivariate time series classification bake off: a review and experimental evaluation of recent algorithmic advances
• A multivariate time series classification based on \(\mu \sigma\)-DWC feature and tree-structured M-SVM

Cites work

• Continuous and Discrete Wavelet Transforms
• scientific article; zbMATH DE number 6378173 (Why is no real title available?)
• Joint dimensionality reduction and metric learning for image set classification
• Robust unsupervised domain adaptation for neural networks via moment alignment

Cited in

(7)

• Multi-period classification: learning sequent classes from temporal domains
• A simple and fast representation space for classifying complex time series
• Multivariate time-series classification with hierarchical variational graph pooling
• Nonnegative matrix factorization with local similarity learning
• A novel multi-task twin-hypersphere support vector machine for classification
• Series2vec: similarity-based self-supervised representation learning for time series classification
• End-to-end deep representation learning for time series clustering: a comparative study

Describes a project that uses

Uses Software

• FaceNet
• UCR Suite

This page was built for publication: A deep multi-task representation learning method for time series classification and retrieval

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2124168)