Convolutional neural networks are an important category of deep learning, currently facing the limitations of electrical frequency and memory access time in massive data processing. Optical computing has been demonstrated to enable significant improvements in terms of processing speeds and energy efficiency. However, most present optical computing schemes are hardly scalable since the number of optical elements typically increases quadratically with the computational matrix size. Here, a compact on-chip optical convolutional processing unit is fabricated on a low-loss silicon nitride platform to demonstrate its capability for large-scale integration. Three 2 × 2 correlated real-valued kernels are made of two multimode interference cells and four phase shifters to perform parallel convolution operations. Although the convolution kernels are interrelated, ten-class classification of handwritten digits from the MNIST database is experimentally demonstrated. The linear scalability of the proposed design with respect to computational size translates into a solid potential for large-scale integration.

The burgeoning volume of parameters in artificial neural network models has posed substantial challenges to conventional tensor computing hardware. Benefiting from the available optical multidimensional information entropy, optical intelligent computing is used as an alternative solution to address the emerging challenges of electrical computing. These limitations, in terms of device size and photonic integration scale, have hindered the performance of optical chips. Herein, an ultrahigh computing density optical tensor processing unit (OTPU), which is grounded in an individual microring resonator (MRR), is introduced to respond to these challenges. Through the independent tuning of multiwavelength lasers, the operational capabilities of an MRR are orchestrated, culminating in the formation of an optical tensor core. This design facilitates the execution of tensor convolution operations via the lightwave and microwave multidomain hybrid multiplexing in terms of the time, wavelength, and frequency of microwaves. The experimental results for the MRR-based OTPU show an extraordinary computing density of 34.04 TOPS/mm². Additionally, the achieved accuracy rate in recognizing MNIST handwritten digits was 96.41%. These outcomes signify a significant advancement toward the realization of high-performance optical tensor processing chips.

A silica-based external cavity narrow linewidth laser is fabricated and experimentally demonstrated based on a commercial silica platform. An add-drop microring resonator and a 2×2 directional coupler in the silica chip form a wavelength-dependent and self-injection-locked external cavity. The linewidth-suppressing effect of the external cavity is theoretically calculated based on the chirp reduction theory, which shows that a long external cavity length at the resonant wavelength can be used to suppress the noise of a free-running laser. In the self-injection locked state, the measured intrinsic linewidth of the fabricated external cavity laser is 27 Hz, which is greatly reduced compared to the 49.7-kHz linewidth of the free-running state. The frequency stability is also measured to be improved by an order of magnitude from 4.52 × 10 ⁻⁸ to 9.07 × 10 ⁻¹⁰ at 1 s averaging time. The proposed narrow-linewidth laser shows the potential for massive production and can be used in various applications such as integrated microwave photonics, LIDAR, high-resolution metrology, and satellite communications.

As a leading branch of deep learning, the convolutional neural network (CNN) is inspired by the natural visual perceptron mechanism of living things, showing great application in image recognition, language processing, and other fields. Photonics technology provides a new route for intelligent signal processing with the dramatic potential of its ultralarge bandwidth and ultralow power consumption, which automatically completes the computing process after the signal propagates through the processor with an analog computing architecture. In this paper, we focus on the key enabling technology of optical CNN, including reviewing the recent advances in the research hotspots, overviewing the current challenges and limitations that need to be further overcome, and discussing its potential application.

For emerging application fields such as autonomous driving and computing vision, which demands the real-time response of massive information, advanced image processing techniques on artificial neural networks (ANNs) are crucial. However, as the complexity of the task increases, the electrical hardware limited by the well-known von Neumann bottleneck is inadequate to meet these extreme requirements in computing speed and computing power. We propose an incoherent optical matrix operator by dynamically manipulating the parameters of the lightwave in terms of the wavelength, time and space to implement the on-demand reconfiguration both in the optical perceptron and optical convolutional processor. For the optical perceptron, it is conducted to perform the case-sensitive classification of 52 English letters. Furthermore, by adjusting the spectral characteristics and output ports, an optical convolution processor is constructed to realize multitask convolution processing for both the image and real-time video. Based on multikernels parallel computing in an optical convolutional layer coupled with an electrically fully connected layer, a convolutional neural network is built to recognize ‘0-9’ handwritten digital images from the Modified National Institute of Standards and Technology (MNIST) database. Owing to the excellent performance of the incoherent beam in terms of the spectral purity, wavelength stability and side-mode suppression ratio, the experimental classification accuracy up to 96.01% greatly matches the theoretical value of 96.67%. Moreover, incoherent information processing is synchronous with data transmission, which releases the requirement of the global clock in digital counterparts. The high-fidelity incoherent convolution processor offers a novel computing framework that serves the next-generation ANN platform.

As the intricacy of network models escalates and the volume of data swells exponentially, the demands on the processing capabilities of neural networks have become increasingly rigorous. Optical computing, with the excellent performance of extremely large bandwidth and ultra-low loss, is poised to be a disruptive technology that supports the needs of the next generation high performance artificial intelligence. In this paper, an optical convolutional neural network, combining a novel architectural design with a compatible data encoding technique, is introduced to achieve superior data efficiency by harnessing the dimensions of wavelength, temporal and parallel space. Utilizing 3×3 convolution kernel on 28×28-pixel images, the proportion of valid data in the output temporal waveform achieves as high as 92.86%. Furthermore, by employing multi-kernel parallel for processing larger size image, the data efficiency is ulteriorly enhanced to an astonishing 99%, and the potential computing power is increased to 10.51 TOPS, showcasing a remarkable leap in performance. During the experiment, five reconfigurable kernels including two positive and three real-value kernels, in conjunction with an electrical fully connected layer, successfully classified handwritten digital images from “0” to “9” in Modified National Institute of Standards and Technology (MNIST) database, achieving an accuracy of 92.81%. The defining feature of the proposed structure is that high-efficiency reconfigurable optical convolutional neural networks streamline the preprocessing and extraction of the data, markedly reducing the invalid data ratio. This innovation, offering a new architecture for optical convolutional neural networks, not only conserves computing power but also improve processing speed, which is expected to alleviate the expanding demand for computing performance in deep learning.