Convolutional echo state network based time series classification method

Abstract

The invention discloses a convolutional echo state network based time series classification method. An echo state network has a time series core and an echo state property, wherein the time series core refers to that the echo state network maps inputted signals into a high-dimensional space of a reserve pool, and the echo state property refers to that the network has a short-term historical information memory capacity. In the convolutional neural network, multi-scale characteristics in the echo state network can be extracted through a multi-scale convolutional layer, and multi-scale time series invariance can be kept through maximal pooling in time direction. By combination of the echo state network and the convolutional neural network, a convolutional echo state network model is provided;by the model for operations including multi-scale convolution, maximal pooling in the time direction and the like of state represent information outputted by the echo state network, advantage complementation of the echo state network and the convolutional neural network is realized, and high efficiency of an echo state network learning mode is kept while advantages of the convolutional neural network in characteristic extraction are achieved.

Description

technical field [0001] The invention relates to the technical field of reserve pool calculation and neural network research, in particular to a time series classification method based on a convolutional echo state network, which is applicable to common multivariate time series classification problems. Background technique [0002] Echo State Network (ESN) is a novel learning method for recurrent neural network. At present, the existing research work on echo state network has been widely used in dynamic system modeling, robot control, chaotic time series prediction and other fields. Its core principle is to realize the modeling of dynamical system through a reserve pool and a simple linear decoder. This reserve pool contains a large number of neuron nodes, and the connections between neuron nodes are randomly initialized and fixed. When this reserve pool receives an input signal of an external time series, it generates a high-dimensional echo state signal with short-term me...

AI Technical Summary

Problems solved by technology

However, the convolutional neural network is very time-consuming in the training process, and the requirements for equipment are often relatively high.

Images