Abstract
We experimentally investigate the performances of an optical reservoir computing (RC) system based on two parallel time-delay reservoirs composed of two semiconductor lasers (SLs) subject to optical feedback. In such a system, the information being processed is split into two parts to send into two reservoirs through directly modulating the pump currents of two SLs, and the temporal output of the two SLs are sampled and taken as the virtual node states for training and testing. Via Santa Fe time series prediction task and multi-waveform recognition task, the performances of the proposed RC system are investigated and compared with those of the system based on one reservoir. The results show that the system based on two parallel reservoirs behaves better performance and stronger parameter robustness than that based on one reservoir. Moreover, through analyzing the dependence of the system performances on the number of virtual node states actually used for readout, the potential data processing rate (DPR) of the system is evaluated. For processing a prediction task under guaranteeing the normalized mean square error below 0.1 and a recognition task under guaranteeing the signal error rate below 0.005, the potential DPR of the proposed RC system can achieve 200 MSa/s, which is twice the DPR of the system with only one reservoir.
Highlights
Nowadays, with the advent of big data era, the demand for efficient information processing technique is growing rapidly
We experimentally investigate the performances of an optical reservoir computing (RC) system based on two parallel time-delay reservoirs composed of two semiconductor lasers (SLs) subject to optical feedback
We experimentally investigate the performance of an optical RC system based on two parallel time-delay reservoirs which are constituted of two distributed feedback SLs (SL1, SL2) subject to optical feedback, respectively
Summary
With the advent of big data era, the demand for efficient information processing technique is growing rapidly. Among ANNs, recurrent neural network (RNN) is capable of performing time-dependent tasks, but it is time-consuming to train the network weights of the input layer, the hidden layer, and the output layer. The reservoir is composed of a large number of nonlinear nodes, and such an RC is usually named as spatially distributed RC [6]. It has been demonstrated that the reservoir in RC can be composed of a single nonlinear node with a time-delay feedback loop, and the corresponding RC is named as time-delay RC (TDRC) [7]. Speaking, TDRC is easier to implement than spatially distributed RC, since its reservoir consists of only a single nonlinear node and a feedback loop. Several groups have implemented TDRCs based on different time-delay systems including electronics [7], [8], optoelectronics [9]–[13], and optics [14]–[17]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
