Research on Sparsity of Output Synapses in Echo State Networks
Joint Authors
Li, Lixiang
Mu, Xiaohui
He, Xiangyu
Source
Mathematical Problems in Engineering
Issue
Vol. 2018, Issue 2018 (31 Dec. 2018), pp.1-12, 12 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2018-12-18
Country of Publication
Egypt
No. of Pages
12
Main Subjects
Abstract EN
This paper presents an improved model of echo state networks (ESNs) and gives the definitions of energy consumption, energy efficiency, etc.
We verify the existence of redundant output synaptic connections by numerical simulations.
We investigate the relationships among energy consumption, prediction step, and the sparsity of ESN.
At the same time, the energy efficiency and the prediction steps are found to present the same variation trend when silencing different synapses.
Thus, we propose a computationally efficient method to locate redundant output synapses based on energy efficiency of ESN.
We find that the neuron states of redundant synapses can be linearly represented by the states of other neurons.
We investigate the contributions of redundant and core output synapses to the performance of network prediction.
For the prediction task of chaotic time series, the predictive performance of ESN is improved about hundreds of steps by silencing redundant synapses.
American Psychological Association (APA)
Mu, Xiaohui& Li, Lixiang& He, Xiangyu. 2018. Research on Sparsity of Output Synapses in Echo State Networks. Mathematical Problems in Engineering،Vol. 2018, no. 2018, pp.1-12.
https://search.emarefa.net/detail/BIM-1205981
Modern Language Association (MLA)
Mu, Xiaohui…[et al.]. Research on Sparsity of Output Synapses in Echo State Networks. Mathematical Problems in Engineering No. 2018 (2018), pp.1-12.
https://search.emarefa.net/detail/BIM-1205981
American Medical Association (AMA)
Mu, Xiaohui& Li, Lixiang& He, Xiangyu. Research on Sparsity of Output Synapses in Echo State Networks. Mathematical Problems in Engineering. 2018. Vol. 2018, no. 2018, pp.1-12.
https://search.emarefa.net/detail/BIM-1205981
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1205981