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.

Based on serial channelization and coherent detection, a radio-frequency (RF) measurement scheme with a Nyquist-bandwidth detector is proposed and experimentally demonstrated. With a wavelength scanning structure, multiple RF channels serial in the time domain are implemented. A coherent receiving module based on an optical hybrid and balanced photodetectors (BPDs) is constructed to reduce the receiver bandwidth and the bandwidth of the follow-up electronic devices. In this paper, a six-channel 3-GHz-spacing channelizer, with 18-GHz receiving bandwidth and 1.5-GHz BPD, is demonstrated. In addition, multifrequency signals and a linear frequency modulation signal with the slope of 4.53 MHz/s are tested.

A serial photonic channelized radio frequency (RF) measurement scheme is proposed and experimentally demonstrated. This scheme can be used for instantaneous multiple-frequency measurement and capturing key parameters of linear frequency modulation signals. Based on high-speed wavelength scanning, this photonic RF channelizer works serially in time domain, and each wavelength labels a certain RF channel. With only one low-bandwidth photodetector (PD), we can implement multiple channel RF frequency measurements, which have a much simpler structure compared with parallel channelized schemes using broadband filter-bank and multiple PDs.

No abstract