Photonic machine learning with on-chip diffractive optics.

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.

On-chip photonic diffractive optical neural network based on a spatial domain electromagnetic propagation model.

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.

Single-shot ultrafast phase retrieval photography.

Single-shot ultrafast photography is a powerful tool for science research and industry applications. In this Letter, a novel strategy for ultrafast imaging of two-dimensional complex (amplitude and phase) objects, which is termed single-shot ultrafast phase retrieval photography (SUP), is proposed and demonstrated. The key component of SUP is a silicon photonic integrated chip, which not only has the function of multi-angle illumination, but also provides ultra-short delays for each illumination source. Combined with an ultra-short pulse source and coherent diffraction imaging, SUP can realize ultrafast single-shot imaging. As a proof of concept, the self-developed multiplexed time delay illumination chip was used for experiments, and we demonstrated the reconstructing of a static complex-valued object with a frame sequence depth of 16 frames from single-shot ptychographic data.

Data and analyses of phase relations in the Ce-Fe-Sb ternary system.

These data and analyses support the research article "Experimental study on phase relations in the Ce-Fe-Sb ternary system" Zhu et al. (2017) [1]. The data and analyses presented here include the experimental results of XRD, SEM and EPMA for the determination of the whole liquidus projection and the isothermal section at 823 K in the Ce-Fe-Sb system. All the results enable the understanding of the constituent phases and the solidification processes of the as-cast alloys as well as the phase relations and the equilibrium regions at 823 K in the Ce-Fe-Sb ternary system over the entire composition.