Search Results (8)

Reservoir computing (RC) is a simple and highly efficient artificial neural network. For such a network, only the output connection weights need training, effectively reducing computational complexity. Optoelectronic time-delayed RC is typically based on an optoelectronic oscillator (OEO) with simultaneous broadband processing capabilities for both optical and electrical signals, while being readily implementable based on existing technologies. In this work, a new OEO-based RC (OEO-RC) using an electroabsorption modulated laser (EML) is designed, and the electroabsorption modulator (EAM) integrated in the EML serves as a nonlinear node. This scheme simplifies the architecture of an OEO-RC. And it is validated by using two typical tasks of the NARMA 10 time series prediction and the handwritten digit image recognition. Numerical results demonstrate that with optimized hyperparameters, this EML-based OEO-RC exhibits a comparable performance compared with some existing photonic time-delayed RCs. Full article

In time-delay reservoir computing (TDRC), mask signal generation techniques in the input layer remain a key factor limiting system integration. In this study, we propose an optical mask generation scheme based on steady–quasi-periodic state switching (S-QPS) dynamics in a semiconductor laser with optical feedback. Experimentally generated S-QPS signals are applied to a TDRC system as mask signals, and the system performance is evaluated using the Santa Fe chaotic time-series prediction task. S-QPS signals are numerically generated based on the Lang–Kobayashi rate equations. The optimal normalized mean square error is 0.027. An analysis of the factors affecting system performance is carried out. The results indicate that period offset has a limited impact on system performance. In contrast, noise-induced amplitude fluctuations have a more pronounced impact. These results provide insights into the use and optimization of S-QPS signals for optical mask generation in TDRC systems. Full article

To improve the accuracy of signal recognition in delay-based optical reservoir computing (RC) systems, this paper proposes the use of nonlinear algorithms at the output layer to replace traditional linear algorithms for training and testing datasets and apply them to the identification of frequency-modulated continuous wave (FMCW) LiDAR signals. This marks the inaugural use of the system for the identification of FMCW LiDAR signals. We elaborate on the fundamental principles of a delay-based optical RC system using an optical-injected distributed feedback laser (DFB) laser and discriminate four FMCW LiDAR signals through this setup. In the output layer, three distinct training algorithms—namely linear regression, support vector machine (SVM), and random forest—were employed to train the optical reservoir. Upon analyzing the experimental results, it was found that regardless of the size of the dataset, the recognition accuracy of the two nonlinear training algorithms was superior to that of the linear regression algorithm. Among the two nonlinear algorithms, the Random Forest algorithm had a higher recognition accuracy than SVM when the sample size was relatively small. Full article

In this work, we present a novel four-channel coherent optical chaotic secure communication (COCSC) system, incorporating four simultaneous photonic reservoir computers in tandem with four coherent demodulation units. We employ a quartet of photonic reservoirs that capture the chaotic dynamics of four polarization components (PCs) emitted by a driving QD spin-VCSEL. These reservoirs are realized utilizing four PCs of a corresponding reservoir QD spin-VCSEL. Through these four concurrent photonic reservoir structures, we facilitate high-quality wideband-chaos synchronization across four pairs of PCs. Leveraging wideband chaos synchronization, our COCSC system boasts a substantial 4 × 100 GHz capacity. High-quality synchronization is pivotal for the precise demasking or decoding of four distinct signal types, QPSK, 4QAM, 8QAM and 16QAM, which are concealed within disparate chaotic PCs. After initial demodulation via correlation techniques and subsequent refinement through a variety of digital signal processing methods, we successfully reconstruct four unique baseband signals that conform to the QPSK, 4QAM, 8QAM and 16QAM specifications. Careful examination of the eye diagrams, bit error rates, and temporal trajectories of the coherently demodulated baseband signals indicates that each set of baseband signals is flawlessly retrieved. This is underscored by the pronounced eye openings in the eye diagrams and a negligible bit error rate for each channel of baseband signals. Our results suggest that delay-based optical reservoir computing employing a QD spin-VCSEL is a potent approach for achieving multi-channel coherent optical secure communication with optimal performance and enhanced security. Full article

As an efficient information processing method, reservoir computing (RC) is essential to artificial neural networks (ANNs). Via the Santa Fe time series prediction task, we numerically investigated the effect of the mismatch of some critical parameters on the prediction performance of the RC based on two mutually delay-coupled semiconductor lasers (SLs) with optical injection. The results show that better prediction performance can be realized by setting appropriate parameter mismatch scenarios. Especially for the situation with large prediction errors encountered in the RC with identical laser parameters, a suitable parameter mismatch setting can achieve computing performance improvement of an order of magnitude. Our research is instructive for the hardware implementation of laser-based RC, where the parameter mismatch is unavoidable. Full article

In the current environment of the explosive growth in the amount of information, the demand for efficient information-processing methods has become increasingly urgent. We propose and numerically investigate a delay-based high-speed reservoir computing (RC) using a circular-side hexagonal resonator (CSHR) microlaser with optical feedback and injection. In this RC system, a smaller time interval can be obtained between virtual nodes, and a higher information processing rate (R_inf) can also be achieved, due to the ultra-short photon lifetime and wide bandwidth of the CSHR microlaser. The performance of the RC system was tested with three benchmark tasks (Santa-Fe chaotic time series prediction task, the 10th order Nonlinear Auto Regressive Moving Average task and Nonlinear channel equalization task). The results show that the system achieves high-accuracy prediction, even with a small number of virtual nodes (25), and is more feasible, with lower requirements for arbitrary waveform generators at the same rate. Significantly, at the high rate of 10 Gbps, low error predictions can be achieved over a large parameter space (e.g., frequency detuning in the interval 80 GHz, injected strength in the range of 0.9 variation and 2% range for feedback strength). Interestingly, it has the potential to achieve R_inf of 25 Gbps under technical advancements. Additionally, its shorter external cavity length and cubic micron scale size make it an excellent choice for large-scale photonic integration reservoir computing. Full article

A delay-laser-based reservoir computer (RC) usually has its processing speed limited by the transient response of laser dynamics. Here, we study a simple all-optical approach to enhancing the processing speed by introducing optical injection to the reservoir layer of conventional RC that consists of a semiconductor laser with a delay loop. Using optical injection, the laser’s transient response effectively accelerates due to the speeded carrier-photon resonance. In the chaotic time-series prediction task, the proposed RC achieves good performance in a flexible range of injection detuning frequency under sufficient injection rate. Using proper injection parameters, the prediction error is significantly reduced and stabilized when using high processing speed. For achieving a prediction error below 0.006, the optical injection enhances the processing speed by an order of magnitude of about 5 GSample/s. Moreover, the proposed RC extends the advantage to the handwritten digit recognition task by achieving better word error rate. Full article

Reservoir computing has rekindled neuromorphic computing in photonics. One of the simplest technological implementations of reservoir computing consists of a semiconductor laser with delayed optical feedback. In this delay-based scheme, virtual nodes are distributed in time with a certain node distance and form a time-multiplexed network. The information processing performance of a semiconductor laser-based reservoir computing (RC) system is usually analysed by way of testing the laser-based reservoir computer on specific benchmark tasks. In this work, we will illustrate the optimal performance of the system on a chaotic time-series prediction benchmark. However, the goal is to analyse the reservoir’s performance in a task-independent way. This is done by calculating the computational capacity, a measure for the total number of independent calculations that the system can handle. We focus on the dependence of the computational capacity on the specifics of the masking procedure. We find that the computational capacity depends strongly on the virtual node distance with an optimal node spacing of 30 ps. In addition, we show that the computational capacity can be further increased by allowing for a well chosen mismatch between delay and input data sample time. Full article