An image classification method based on Echo State Network
Authors:
- 15 October 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 165-170
Abstract
As a traditional neural network architecture, Echo State Network(ESN) has achieved good results in time series forecasting. However, in the past ten years, few people have conducted research on its application to images, especially in classification tasks. Echo State Network is a kind of Recurrent Neural Network, it has the advantages of simple structure and convenient training. It only needs to train its output weight $w_{out}$ , which saves a lot of time and resources. In this article, we input the whole picture into ESN in multi-input mode to classify images, and use the traditional Long Short-Term Memory(LSTM) model to compare experiments with it, and the results found that esn has better stability and accuracy.
Keywords
Funding Information
- National Key Research and Development Program of China (2020YFB1805402)
- National Natural Science Foundation of China (62032002,61932005)
- 111 Project (B21049)
This publication has 19 references indexed in Scilit:
- Coherence Constrained Graph LSTM for Group Activity RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2019
- Prediction Using Cuckoo Search Optimized Echo State NetworkArabian Journal for Science and Engineering, 2019
- AT-LSTM: An Attention-based LSTM Model for Financial Time Series PredictionIOP Conference Series: Materials Science and Engineering, 2019
- Consistency in echo-state networksChaos: An Interdisciplinary Journal of Nonlinear Science, 2019
- Echo state networks are universalNeural Networks, 2018
- Network Traffic Prediction Method Based on Improved Echo State NetworkIEEE Access, 2018
- TD-LSTM: Temporal Dependence-Based LSTM Networks for Marine Temperature PredictionSensors, 2018
- Growing Echo-State Network With Multiple SubreservoirsIEEE Transactions on Neural Networks and Learning Systems, 2016
- Fabric Image Edge Detection Based on Octonion and Echo State NetworksApplied Mechanics and Materials, 2014
- Echo state networkScholarpedia, 2007