End-to-end Learning for Early Classification of Time Series

Abstract : Classification of time series is a topical issue in machine learning. While accuracy stands for the most important evaluation criterion, some applications require decisions to be made as early as possible. Optimization should then target a compromise between earliness, i.e., a capacity of providing a decision early in the sequence, and accuracy. In this work, we propose a generic, end-to-end trainable framework for early classification of time series. This framework embeds a learnable decision mechanism that can be plugged into a wide range of already existing models. We present results obtained with deep neural networks on a diverse set of time series classification problems. Our approach compares well to state-of-the-art competitors while being easily adaptable by any existing neural network topology that evaluates a hidden state at each time step.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-02174314
Contributor : Nicolas Courty <>
Submitted on : Friday, July 5, 2019 - 9:14:10 AM
Last modification on : Sunday, July 7, 2019 - 1:34:02 AM

Links full text

Identifiers

  • HAL Id : hal-02174314, version 1
  • ARXIV : 1901.10681

Citation

Marc Rußwurm, Sébastien Lefevre, Nicolas Courty, Rémi Emonet, Marco Körner, et al.. End-to-end Learning for Early Classification of Time Series. 2019. ⟨hal-02174314⟩

Share

Metrics

Record views

33