The emergence of parallel convolution-operation technology has substantially powered the complexity and functionality of optical neural networks (ONN) by harnessing the dimension of optical wavelength. However, this advanced architecture faces remarkable challenges in high-level integration and on-chip operation. In this work, convolution based on time-wavelength plane stretching approach is implemented on a microcomb-driven chip-based photonic processing unit (PPU). To support the operation of this processing unit, we develop a dedicated control and operation protocol, leading to a record high weight precision of 9 bits. Moreover, the compact architecture and high data loading speed enable a preeminent photonic-core compute density of over 1 trillion of operations per second per square millimeter (TOPS mm⁻²). Two proof-of-concept experiments are demonstrated, including image edge detection and handwritten digit recognition, showing comparable processing capability compared to that of a digital computer. Due to the advanced performance and the great scalability, this parallel photonic processing unit can potentially revolutionize sophisticated artificial intelligence tasks including autonomous driving, video action recognition and image reconstruction.

Tensor analytics lays the mathematical basis for the prosperous promotion of multiway signal processing. To increase computing throughput, mainstream processors transform tensor convolutions into matrix multiplications to enhance the parallelism of computing. However, such order-reducing transformation produces data duplicates and consumes additional memory. Here, we propose an integrated photonic tensor flow processor (PTFP) without digitally duplicating the input data. It outputs the convolved tensor as the input tensor ‘flows’ through the processor. The hybrid manipulation of optical wavelengths, space dimensions, and time delay steps, enables the direct representation and processing of high-order tensors in the optical domain. In the proof-of-concept experiment, an integrated processor manipulating wavelengths and delay steps is implemented for demonstrating the key functionalities of PTFP. The multi-channel images and videos are processed at the modulation rate of 20 Gbaud. A convolutional neural network for video action recognition is demonstrated on the processor, which achieves an accuracy of 97.9%.

Optical implementations of neural networks (ONNs) herald the next-generation high-speed and energy-efficient deep learning computing by harnessing the technical advantages of large bandwidth and high parallelism of optics. However, due to the problems of the incomplete numerical domain, limited hardware scale, or inadequate numerical accuracy, the majority of existing ONNs were studied for basic classification tasks. Given that regression is a fundamental form of deep learning and accounts for a large part of current artificial intelligence applications, it is necessary to master deep learning regression for further development and deployment of ONNs. Here, we demonstrate a silicon-based optical coherent dot-product chip (OCDC) capable of completing deep learning regression tasks. The OCDC adopts optical fields to carry out operations in the complete real-value domain instead of in only the positive domain. Via reusing, a single chip conducts matrix multiplications and convolutions in neural networks of any complexity. Also, hardware deviations are compensated via in-situ backpropagation control provided the simplicity of chip architecture. Therefore, the OCDC meets the requirements for sophisticated regression tasks and we successfully demonstrate a representative neural network, the AUTOMAP (a cutting-edge neural network model for image reconstruction). The quality of reconstructed images by the OCDC and a 32-bit digital computer is comparable. To the best of our knowledge, there is no precedent of performing such state-of-the-art regression tasks on ONN chips. It is anticipated that the OCDC can promote the novel accomplishment of ONNs in modern AI applications including autonomous driving, natural language processing, and scientific study.

This paper proposes a novel reflectometry based on the frequency modulation pulse-compression technology, called optical pulse compression reflectometry (OPCR). Linear frequency modulation (LFM) pulse is taken as an example to implement the OPCR. Its working principle and theoretical analysis are demonstrated. The spatial resolution is determined by the sweeping range of the LFM rather than the pulse width, which overcomes the tradeoff between spatial resolution and measurement range in the conventional pulse-based optical time domain reflectometry. The influence of the laser’s phase noise on the integrated side lobe ratio and peak side lobe ratio is theoretically studied. Thanks to the continuous acquisition nature of the OPCR, time averaging is valid to eliminate the influence and results in the measurement range of the OPCR beyond a few times of the source coherent length. A proof-of-concept experiment of the OPCR is carried out to verify the spatial resolution and measurement range.

Radar has been widely used for military, security and rescue purposes and modern radar should be reconfigurable at multi-bands and have programmable central frequencies and considerable bandwidth agility. Microwave photonics or photonics-assisted radio-frequency technology is a unique solution to providing such capabilities. Here, we demonstrate an all-optical central-frequency-programmable and bandwidth-tailorable radar architecture that provides a coherent system and utilizes one mode-locked laser for both signal generation and reception. Heterodyning of two individually filtered optical pulses that are pre-chirped via wavelength-to-time mapping generates a wideband linearly chirped radar signal. The working bands can be flexibly tailored with the desired bandwidth at a user-preferred carrier frequency. Radar echoes are first modulated onto the pre-chirped optical pulse, which is also used for signal generation and then stretched in time or compressed in frequency several fold based on the time-stretch principle. Thus, digitization is facilitated without loss of detection ability. We believe that our results demonstrate an innovative radar architecture with an ultra-high-range resolution.

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.