Collective dynamics of rate neurons for supervised learning in a reservoir computing system

2019 ◽  
Vol 29 (10) ◽  
pp. 103126 ◽  
Author(s):  
Oleg V. Maslennikov ◽  
Vladimir I. Nekorkin
Keyword(s):  
Supervised Learning ◽  
Computing System ◽  
Reservoir Computing ◽  
Collective Dynamics

Hardware-Optimized Reservoir Computing System for Edge Intelligence Applications

2021 ◽  
Author(s):  
Alejandro Morán ◽  
Vincent Canals ◽  
Fabio Galan-Prado ◽  
Christian F. Frasser ◽  
Dhinakar Radhakrishnan ◽  
...  
Keyword(s):  
Computing System ◽  
Reservoir Computing

Reservoir Computing System using Biomolecular Memristor

2021 ◽  
Author(s):  
Md Razuan Hossain ◽  
Joseph S. Najem ◽  
Tauhidur Rahman ◽  
Md Sakib Hasan
Keyword(s):  
Computing System ◽  
Reservoir Computing

Temporal data classification and forecasting using a memristor-based reservoir computing system

2019 ◽  
Vol 2 (10) ◽  
pp. 480-487 ◽  
Author(s):  
John Moon ◽  
Wen Ma ◽  
Jong Hoon Shin ◽  
Fuxi Cai ◽  
Chao Du ◽  
...  
Keyword(s):  
Data Classification ◽  
Computing System ◽  
Reservoir Computing ◽  
Temporal Data

Performance optimization of a reservoir computing system based on a solitary semiconductor laser under electrical-message injection

2020 ◽  
Vol 59 (23) ◽  
pp. 6932
Author(s):  
Qingqing Zeng ◽  
Zhengmao Wu ◽  
Dianzuo Yue ◽  
Xiangsheng Tan ◽  
Junyao Tao ◽  
...  
Keyword(s):  
Semiconductor Laser ◽  
Performance Optimization ◽  
Computing System ◽  
Reservoir Computing

scholarly journals A Multiple-Input Multiple-Output Reservoir Computing System Subject to Optoelectronic Feedbacks and Mutual Coupling

Entropy ◽  
2020 ◽  
Vol 22 (2) ◽  
pp. 231 ◽  
Author(s):  
Xiurong Bao ◽  
Qingchun Zhao ◽  
Hongxi Yin
Keyword(s):  
Mutual Coupling ◽  
Signal To Noise Ratio ◽  
Multiple Input Multiple Output ◽  
Computing System ◽  
Error Rates ◽  
Reservoir Computing ◽  
Multiple Input ◽  
Input Multiple Output ◽  
High Recognition Accuracy ◽  
Mean Square Errors

In this paper, a multiple-input multiple-output reservoir computing (RC) system is proposed, which is composed of multiple nonlinear nodes (Mach–Zehnder modulators) and multiple mutual-coupling loops of optoelectronic delay lines. Each input signal is added into every mutual-coupling loop to implement the simultaneous recognition of multiple route signals, which results in the signal processing speed improving and the number of routes increasing. As an example, the four-route input and four-route output RC is simultaneously realized by numerical simulations. The results show that this type of RC system can successfully recognize the four-route optical packet headers with 3-bit, 8-bit, 16-bit, and 32-bit, and four-route independent digital speeches. When the white noise is added to the signals such that the signal-to-noise ratio (SNR) of the optical packet headers and the digital speeches are 35 dB and 20 dB respectively, the normalized root mean square errors (NRMSEs) of the signal recognition are all close to 0.1. The word error rates (WERs) of the optical packet header recognition are 0%. The WER of the digital speech recognition is 1.6%. The eight-route input and eight-route output RC is also numerically simulated. The recognition of the eight-route 3-bit optical packet headers is implemented. The parallel processing of multiple-route signals and the high recognition accuracy are implemented by this proposed system.

Sign in / Sign up

Export Citation Format

Share Document