17 July 2019 in Light: Science & Applications
Analog-to-digital converters (ADCs) must be high speed, broadband, and accurate for the development of modern information systems, such as radar, imaging, and communications systems; photonic technologies are regarded as promising technologies for realizing these advanced requirements. Here, we present a deep-learning-powered photonic ADC architecture that simultaneously exploits the advantages of electronics and photonics and overcomes the bottlenecks of the two technologies, thereby overcoming the ADC tradeoff among speed, bandwidth, and accuracy. Via supervised training, the adopted deep neural networks learn the patterns of photonic system defects and recover the distorted data, thereby maintaining the high quality of the electronic quantized data succinctly and adaptively. The numerical and experimental results demonstrate that the proposed architecture outperforms state-of-the-art ADCs with developable high throughput; hence, deep learning performs well in photonic ADC systems. We anticipate that the proposed architecture will inspire future high-performance photonic ADC design and provide opportunities for substantial performance enhancement for the next-generation information systems.
19 July 2023 in Optics Letters
We experimentally demonstrate an all-optical nonlinear activation unit based on the injection-locking effect of distributed feedback laser diodes (DFB-LDs). The nonlinear carrier dynamics in the unit generates a low-threshold nonlinear activation function with optimized operating conditions. The unit can operate at a low threshold of −15.86 dBm and a high speed of 1 GHz, making it competitive among existing optical nonlinear activation approaches. We apply the unit to a neural network task of solving the second-order ordinary differential equation. The fitting error is as low as 0.0034, verifying the feasibility of our optical nonlinear activation approach. Given that the large-scale fan-out of optical neural networks (ONNs) will significantly reduce the optical power in one channel, our low-threshold scheme is suitable for the development of high-throughput ONNs.
21 December 2021 in Photonics Research
It is believed that neural information representation and processing relies on the neural population instead of a single neuron. In neuromorphic photonics, photonic neurons in the form of nonlinear responses have been extensively studied in single devices and temporal nodes. However, to construct a photonic neural population (PNP), the process of scaling up and massive interconnections remain challenging considering the physical complexity and response latency. Here, we propose a comb-based PNP interconnected by carrier coupling with superior scalability. Two unique properties of neural population are theoretically and experimentally demonstrated in the comb-based PNP, including nonlinear response curves and population activities coding. A classification task of three input patterns with dual radio-frequency (RF) tones is successfully implemented in a time-efficient manner, which allows the comb-based PNP to make effective use of the ultra-broad bandwidth of photonics for parallel and nonlinear processing.
31 March 2022 in Materials Letters
1 May 2023 in IEEE Journal of Selected Topics in Quantum Electronics
The real-time massive-data intelligent information processing tasks highlight a vital requirement for the novel, intelligent optimization hardware. Convolutional neural networks are highly capable of extracting the hierarchical feature map and enhancing recognition accuracy, with photonics-enabled implementations drawing considerable interest. Here, we propose a large-scale and reconfigurable photonic convolutional neural network (PCNN), based on a hardware-friendly distributed feedback laser diode (DFB-LD). Our approach applies biological time-to-first-spike coding to a DFB-LD neuron to perform a temporal convolutional operation (TCO) for image processing tasks. In PCNN, experimental results demonstrate that we successfully implement the TCO to extract the image features with convolutional kernels of size 11×11. Furthermore, we investigate the temporal pulse shaping of a DFB-LD neuron to build a densely-connected fully connected layer, which synaptic weights can be rapidly adjusted at a rate of 5 GHz, achieving full MNIST and Fashion-MNIST benchmark image classification tasks, with classification accuracies of 98.56% and 87.48%, respectively. This work highlights the potential of neuron-like optical analog computing platforms for real-time and more complex intelligent processing networks.