A unified information perceptron using deep reservoir computing. (July 2020)

• Record Type: Journal Article
• Authors: An, Qiyuan; Bai, Kangjun; Liu, Lingjia; Shen, Fangyang; Yi, Yang
• Is Part Of: Computers & electrical engineering. Volume 85(2020)
• Publication Date: 2020-07
• Subjects: Reservoir computing -- Delay feedback reservoir -- Deep neural network -- Image classification -- Speech recognition; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2020.106705
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: The delay feedback reservoir, as a branch of reservoir computing, has attracted a wide range of research interests because of its training efficiency and its simplicity for hardware implementation. However, its potential for processing various kinds of data, like sequential and matrix data, has not been fully explored. In this paper, we present a unified information processing structure by fusing the convolutional or fully connected neural network with the delay feedback reservoir into a hybrid neural network model to accomplish the comprehensive information processing goal. Our experimental results show that our methodology achieves high accuracy in both image classification and speech recognition, yielding 99.03% testing accuracy on the handwritten digits dataset (MNIST) and 97.3% on Spoken Digits Command Dataset (SDCD).