Enhanced memory capacity of a neuromorphic reservoir computing system based on a VCSEL with double optical feedbacks

Guo, Xingxing; Xiang, Shuiying; Zhang, Yahui; Wen, Aijun

doi:10.1007/s11432-020-2862-7

Cited by 9 publications

(4 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this test, we generate 4000 points data of u(i), where the first 1000 points are used to initialize the system, and the next 2000 points and 1000 points are used for training and testing, respectively. We noticed that the MC obtained in [36] based on multiple lasers subject to parallel optical feedback is about 11, the MC achieved in [25] is about 16 based on a VCSEL subject to optical feedback, and the highest MC achieved in [40] based on a VCSEL subject to double optical feedback is about 24.5. Therefore, we select a moderate value of 16 as the threshold value for high fading memory in this work.…”

Section: Memory Capacitymentioning

confidence: 86%

Reservoir Computing Based on Two Parallel Reservoirs Under Identical Electrical Message Injection

Yue

Hou

et al. 2021

IEEE Photonics J.

View full text Add to dashboard Cite

In this work, we propose and numerically investigate a scheme for reservoir computing (RC) based on two parallel reservoirs under identical electrical message injection, in which two semiconductor lasers (SLs) under optical feedback are utilized as two parallel reservoirs. For simplifying the system, only one mask signal is employed in this scheme. After multiplying with input data, the masked information is injected into two parallel reservoir lasers (SL1 and SL2). The virtual node states can be obtained from the temporal outputs of two SLs. RC can be accomplished by three ways, namely RC1/RC2 (the virtual node states originating from SL1/SL2 are used for training and testing) and RCM (the merged virtual node states originating from two SLs are used for training and testing). Via chaotic time series prediction task and memory capacity (MC) test, the performance of the RC system is simulated and assessed. The results show that, for a given data processing rate, better prediction performance and higher MC can be realized by RCM through setting suitable mismatched parameters between the two SLs. Under satisfying the requirement for achieving a good performance, the highest data processing rate can be doubled for RCM with respect to that for RC1/RC2.

show abstract

Section: Memory Capacitymentioning

confidence: 86%

Reservoir Computing Based on Two Parallel Reservoirs Under Identical Electrical Message Injection

Yue

Hou

et al. 2021

IEEE Photonics J.

View full text Add to dashboard Cite

show abstract

“…An attempt at the time-delay RC systems based on VC-SEL is that we proposed a four-channels RC system based on polarization dynamics in mutually coupled VCSELs [67] . As shown in Fig.…”

Section: Photonic Reservoir Computingmentioning

confidence: 99%

A review: Photonics devices, architectures, and algorithms for optical neural computing

et al. 2021

Self Cite

View full text Add to dashboard Cite

The explosive growth of data and information has motivated various emerging non-von Neumann computational approaches in the More-than-Moore era. Photonics neuromorphic computing has attracted lots of attention due to the fascinating advantages such as high speed, wide bandwidth, and massive parallelism. Here, we offer a review on the optical neural computing in our research groups at the device and system levels. The photonics neuron and photonics synapse plasticity are presented. In addition, we introduce several optical neural computing architectures and algorithms including photonic spiking neural network, photonic convolutional neural network, photonic matrix computation, photonic reservoir computing, and photonic reinforcement learning. Finally, we summarize the major challenges faced by photonic neuromorphic computing, and propose promising solutions and perspectives.

show abstract

“…Thus, it is a possible method to improve the identification accuracy by leveraging a more complex random sequence as the mask signal, e.g., chaos [47]. Moreover, the scheme of multiple optical feedback can be introduced to improve the performance of the time-delayed RC [22,48], where the RL has a more complex response compared with an RC system with single optical feedback. Furthermore, the identification accuracy can be further improved by leveraging other image feature extraction methods, such as untrained CNNs [16,21], which may contain more information and details of images.…”

Section: (A) [Red Line]mentioning

confidence: 99%

“…Benefiting from the all-optical structure, fast response, and complex dynamic properties, time-delayed RC consisting of semiconductor lasers (SLs) as an alternative approach to performing various tasks, including chaotic time-series prediction, wave identification, and speech recognition [19,20,[22][23][24]. In particular, a phased laser array, as a highly integrated and extensible framework, offers the capacity to be readily fabricated on a single chip, which shows the promise to achieve high-performance time-delayed RC.…”

Section: Introductionmentioning

confidence: 99%

Time-Delayed Reservoir Computing Based on a Two-Element Phased Laser Array for Image Identification

et al. 2021

View full text Add to dashboard Cite

We report on a simple approach of time-delayed reservoir computing (RC) based on a two-element phased laser array for image identification. Here the phased laser array with optical feedback and injection is trained according to the representative characteristics extracted through histograms of oriented gradients. These characteristic vectors are multiplied by a random mask signal to form input data, which are subsequently trained in the reservoir. By optimizing the parameters of the RC, we achieve an identification accuracy of 97.44% on the MNIST dataset and 85.46% on the Fashion-MNIST dataset. These results indicate that our proposed RC indeed allows accurate classification of handwritten digit and fashion production. Moreover, we further forecast an RC scheme based on a larger-scale phased laser array, which is expected to tackle more complex tasks at a high speed. Our work offers a possibility for advanced image processing using highly integrated neuromorphic photonic systems.

show abstract

Enhanced memory capacity of a neuromorphic reservoir computing system based on a VCSEL with double optical feedbacks

Cited by 9 publications

References 45 publications

Reservoir Computing Based on Two Parallel Reservoirs Under Identical Electrical Message Injection

Reservoir Computing Based on Two Parallel Reservoirs Under Identical Electrical Message Injection

A review: Photonics devices, architectures, and algorithms for optical neural computing

Time-Delayed Reservoir Computing Based on a Two-Element Phased Laser Array for Image Identification

Contact Info

Product

Resources

About