Adaptive time-delayed photonic reservoir computing based on Kalman-filter training

Adaptive time-delayed photonic reservoir computing based on Kalman-filter training

We propose an adaptive time-delayed photonic reservoir computing (RC) structure by utilizing the Kalman filter (KF) algorithm as training approach. Two benchmark tasks, namely the Santa Fe time-series prediction and the nonlinear channel equalization, are adopted to evaluate the performance of the p...

Full description

Bibliographic Details
Main Authors: Feng, W. (Author), Jiang, N. (Author), Jin, J. (Author), Liu, S. (Author), Peng, J. (Author), Qiu, K. (Author), Zhang, Q. (Author), Zhang, Y. (Author), Zhao, A. (Author)
Format: Article
Language:English
Published: Optica Publishing Group (formerly OSA) 2022
Subjects:
Adaptive kalman filter
Benchmarking
Chaotic signal
Equalizers
Forecasting
Kalman filter algorithms
Kalman filters
Least Square
Nonlinear channels equalization
Performance
Photonic reservoir computing
Reservoir Computing
Time delay
Time delayed
Time series prediction
Online Access:View Fulltext in Publisher

Internet

View Fulltext in Publisher

Similar Items