Time series classification with Echo Memory Networks

Abstract

a b s t r a c tEcho state networks (ESNs) are randomly connected recurrent neural networks (RNNs) that can be used as a temporal kernel for modeling time series data, and have been successfully applied on time series prediction tasks. Recently, ESNs have been applied to time series classification (TSC) tasks. However, previous ESN-based classifiers involve either training the model by predicting the next item of a sequence, or predicting the class label at each time step. The former is essentially a predictive model adapted from time series prediction work, rather than a model designed specifically for the classification task. The latter approach only considers local patterns at each time step and then averages over the classifications. Hence, rather than selecting the most discriminating sections of the time series, this approach will incorporate non-discriminative information into the classification, reducing accuracy. In this paper, we propose a novel end-to-end framework called the Echo Memory Network (EMN) in which the time series dynamics and multi-scale discriminative features are efficiently learned from an unrolled echo memory using multi-scale convolution and max-over-time pooling. First, the time series data are projected into the high dimensional nonlinear space of the reservoir and the echo states are collected into the echo memory matrix, followed by a single multi-scale convolutional layer to extract multi-scale features from the echo memory matrix. Max-over-time pooling is used to maintain temporal invariance and select the most important local patterns. Finally, a fully-connected hidden layer feeds into a softmax layer for classification. This architecture is applied to both time series classification and human action recognition datasets. For the human action recognition datasets, we divide the action data into five different components of the human body, and propose two spatial information fusion strategies to integrate the spatial information over them. With one training-free recurrent layer and only one layer of convolution, the EMN is a very efficient end-to-end model, and ranks first in overall classification ability on 55 TSC benchmark datasets and four 3D skeleton-based human action recognition tasks.

New Neural Network Corresponding to the Evolution Process of the Brain

“…On the other hand, if Hjs > T > Hjp, the serial data is received from the lower layer in the states R 0 , R 1 ,., R m , and the conversion result is output to the upper layer. In both conversions, when the conversion of the last data is completed, the end signal is transmitted toward the upper layer [4]. This state is E and next returns to the initial standby state S. Even time series data with a deep context can be processed by arranging Basic Units in layers.…”

Time series classification: nearest neighbor versus deep learning models

“…Inspired by the Inception-v4 architecture used for computer vision tasks, Fawaz et al [18] proposes Incep-tionTime as an ensemble of deep convolutional neural network models and achieves a higher accuracy with a less time consumption, compared with the HIVE-COTE algorithm. Ma et al [34] proposes a end-to-end framework called the Echo Memory Network, which uses echo state networks to learn the time series dynamics and multi-scale discriminative features.…”

Lagged encoding for image‐based time series classification using convolutional neural networks

“…Alternatively, plain classifiers may be launched on time series data points after some transformations. Recently, CNN‐based plain classifier and Recurrent Neural Networks were applied to process numerical time series with a great success.…”