TimeNet: Pre-trained deep recurrent neural network for time series classification
arXiv:1706.08838
Abstract
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.
25th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, 2017, Bruges, Belgium
References in corpus (5)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- Recurrent Neural Network Regularization
- LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection
- Multi-Sensor Prognostics using an Unsupervised Health Index based on LSTM Encoder-Decoder