传统的信号、信息处理流程相对独立且繁琐，人工智能（AI）技术通过引入“信号变换+信息识别”的处理策略，提升了整体处理的智能化水平。然而，未来应用中信号与信息高度密集，要求更高的系统能效、更灵活的决策能力。文中提出了通过光电融合与集成技术有望实现信号与信息兼容一体的新型处理范式：利用光子与电子技术在电磁尺度、物理性质、实现方法等层面的互补优势，针对信号与信息整体进行直接处理，并且具有融合深层智能技术的潜力。回顾了光电融合形式下的新兴信号与信息处理体制，指出了光电混合集成对光电融合处理技术的重要支撑意义。

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.

We propose an optical tensor core (OTC) architecture for neural network training. The key computational components of the OTC are the arrayed optical dot-product units (DPUs). The homodyne-detection-based DPUs can conduct the essential computational work of neural network training, i.e., matrix-matrix multiplication. Dual-layer waveguide topology is adopted to feed data into these DPUs with ultra-low insertion loss and cross talk. Therefore, the OTC architecture allows a large-scale dot-product array and can be integrated into a photonic chip. The feasibility of the OTC and its effectiveness on neural network training are verified with numerical simulations.

We demonstrate a photonic architecture to enable the separation of ultra-wideband signals. The architecture consists of a channel-interleaved photonic analog-to-digital converter (PADC) and a dilated fully convolutional network (DFCN). The aim of the PADC is to perform ultra-wideband signal acquisition, which introduces the mixing of signals between different frequency bands. To alleviate the interference among wideband signals, the DFCN is applied to reconstruct the waveform of the target signal from the ultra-wideband mixed signals in the time domain. The channel-interleaved PADC provides a wide spectrum reception capability. Relying on the DFCN reconstruction algorithm, the ultra-wideband signals, which are originally mixed up, are effectively separated. Additionally, experimental results show that the DFCN reconstruction algorithm improves the average bit error rate by nearly three orders of magnitude compared with that without the algorithm.

This Letter investigates the impact of the photodiode (PD) saturation in a sub-sampled photonic analog-to-digital converter (PADC) with two individual pulse lasers. It is essentially proved that when the optical power to the saturated PD increases, the optical–electrical conversion (OEC) responsivity and digitized output power of the PADC decrease. If femtosecond pulses are employed for the PADC sampling clock, the time-stretching process in a dispersive medium is necessary to decrease the impact of the PD saturation. In contrast, when the sampling clock with picosecond pulses is utilized, the PD saturation is more tolerable, and thus, the OEC responsivity can be improved by an increase of the optical power to the PD no matter if the time-stretching process is employed.

We experimentally demonstrate the ultra-high range resolution of a photonics-based microwave radar using a high repetition rate actively mode-locked laser (AMLL). The transmitted signal and sampling clock in the radar originate from the same AMLL to achieve a large instantaneous bandwidth. A Ka band linearly frequency modulated signal with a bandwidth up to 8 GHz is successfully generated and processed with the electro-optical upconversion and direct photonic sampling. The minor lobe suppression (MLS) algorithm is adopted to enhance the dynamic range at a cost of the range resolution. Two-target discrimination with the MLS algorithm proves the range resolution reaches 2.8 cm. The AMLL-based microwave-photonics radar shows promising applications in high-resolution imaging radars having the features of high-frequency band and large bandwidth.