An integrated physical diffractive optical neural network (DONN) is proposed based on a standard silicon-on-insulator (SOI) substrate. This DONN has compact structure and can realize the function of machine learning with whole-passive fully-optical manners. The DONN structure is designed by the spatial domain electromagnetic propagation model, and the approximate process of the neuron value mapping is optimized well to guarantee the consistence between the pre-trained neuron value and the SOI integration implementation. This model can better ensure the manufacturability and the scale of the on-chip neural network, which can be used to guide the design and manufacturing of the real chip. The performance of our DONN is numerically demonstrated on the prototypical machine learning task of prediction of coronary heart disease from the UCI Heart Disease Dataset, and accuracy comparable to the state-of-the-art is achieved.

Machine learning technologies have been extensively applied in high-performance information-processing fields. However, the computation rate of existing hardware is severely circumscribed by conventional Von Neumann architecture. Photonic approaches have demonstrated extraordinary potential for executing deep learning processes that involve complex calculations. In this work, an on-chip diffractive optical neural network (DONN) based on a silicon-on-insulator platform is proposed to perform machine learning tasks with high integration and low power consumption characteristics. To validate the proposed DONN, we fabricated 1-hidden-layer and 3-hidden-layer on-chip DONNs with footprints of 0.15 mm2 and 0.3 mm2 and experimentally verified their performance on the classification task of the Iris plants dataset, yielding accuracies of 86.7% and 90%, respectively. Furthermore, a 3-hidden-layer on-chip DONN is fabricated to classify the Modified National Institute of Standards and Technology handwritten digit images. The proposed passive on-chip DONN provides a potential solution for accelerating future artificial intelligence hardware with enhanced performance.

As one of the most important optical filtering devices, Bragg gratings have been extensively used in various systems. A long Bragg grating is desired for many applications including frequency selection in semiconductor lasers and dispersion control for ultra-short pulses. As a prominent example, integrated spiral Bragg grating waveguides (SBGWs) have drawn much attention in the years. However, until now, the length of an integrated grating is still limited to a few milli-meters due to total waveguide loss. In this work, we propose and demonstrate a novel long chirped SBGW with waveguide loss as low as 0.05 dB/cm on a silicon nitride (Si3N4) platform. A 13.8 cm SBGW is fabricated, which is the longest on-chip waveguide grating reported so far. The SBGW’s reflection bandwidth is 9.2 nm from 1556.3 nm to 1565.5 nm, and it provides a total of 1440 ps group delay, that is, −156.5 ps/nm of dispersion. The group delay response shows great linearity and temperature stability. This integrated device holds great potential for various applications including in-line dispersion compensation, optical true delay phase array, and microwave photonics.

Ever-growing deep-learning technologies are making revolutionary changes for modern life. However, conventional computing architectures are designed to process sequential and digital programs but are burdened with performing massive parallel and adaptive deep-learning applications. Photonic integrated circuits provide an efficient approach to mitigate bandwidth limitations and the power-wall brought on by its electronic counterparts, showing great potential in ultrafast and energy-free high-performance computation. Here, we propose an optical computing architecture enabled by on-chip diffraction to implement convolutional acceleration, termed “optical convolution unit” (OCU). We demonstrate that any real-valued convolution kernels can be exploited by the OCU with a prominent computational throughput boosting via the concept of structral reparameterization. With the OCU as the fundamental unit, we build an optical convolutional neural network (oCNN) to implement two popular deep learning tasks: classification and regression. For classification, Fashion Modified National Institute of Standards and Technology (Fashion-MNIST) and Canadian Institute for Advanced Research (CIFAR-4) data sets are tested with accuracies of 91.63% and 86.25%, respectively. For regression, we build an optical denoising convolutional neural network to handle Gaussian noise in gray-scale images with noise level σ=10, 15, and 20, resulting in clean images with an average peak signal-to-noise ratio (PSNR) of 31.70, 29.39, and 27.72 dB, respectively. The proposed OCU presents remarkable performance of low energy consumption and high information density due to its fully passive nature and compact footprint, providing a parallel while lightweight solution for future compute-in-memory architecture to handle high dimensional tensors in deep learning.

A new method to improve the integration level of an on-chip diffractive optical neural network (DONN) is proposed based on a standard silicon-on-insulator (SOI) platform. The metaline, which represents a hidden layer in the integrated on-chip DONN, is composed of subwavelength silica slots, providing a large computation capacity. However, the physical propagation process of light in the subwavelength metalinses generally requires an approximate characterization using slot groups and extra length between adjacent layers, which limits further improvements of the integration of on-chip DONN. In this work, a deep mapping regression model (DMRM) is proposed to characterize the process of light propagation in the metalines. This method improves the integration level of on-chip DONN to over 60,000 and elimnates the need for approximate conditions. Based on this theory, a compact-DONN (C-DONN) is exploited and benchmarked on the Iris plants dataset to verify the performance, yielding a testing accuracy of 93.3%. This method provides a potential solution for future large-scale on-chip integration.

No abstract

A miniature on-chip diffractive optical neural network (DONN) with a footprint of 1.35 × 10 – 3mm2 is designed through the particle swarm optimization (PSO) algorithm, yielding an accuracy of 93.3% in simulation on the Iris plants dataset.

Machine learning technologies have been extensively applied in high-performance information-processing fields. However, the computation rate of current hardware is severely circumscribed by the conventional Von Neumann architecture. Photonic approaches have demonstrated extraordinary potential for executing deep learning involving complex calculations. In this work, an on-chip diffractive optical neural network (DONN) based on a silicon-on-insulator (SOI) platform is proposed to perform machine learning tasks with high integration and low power consumption. To validate the proposed DONN, we fabricated 1-hidden-layer and 3-hidden-layer on-chip DONNs with footprints of 0.15 mm2 and 0.3 mm2 and experimentally verified their performance in a classification task on the Iris plants dataset, yielding accuracies of 86.7% and 90%, respectively. The proposed fully passive on-chip DONN provides a potential solution for accelerating future artificial intelligence hardware with enhanced performance.