Running summarizing tools on a new article

Check the paper below, then start its synthesis.


Space-efficient optical computing with an integrated chip diffractive neural network

Hanqing Zhu (Nanyang Technological University), Jun Zou (Nanyang Technological University), Hui Zhang (Nanyang Technological University), Yuzhi Shi (Shanghai Jiao Tong University), Sihui Luo (Nanyang Technological University), N. Wang (Agency for Science, Technology and Research, Nanyang Technological University), Hong Nian Cai (Agency for Science, Technology and Research, Institute of Microelectronics), Lingxiao Wan (Nanyang Technological University), Bo Wang (Nanyang Technological University), Xudong Jiang (Nanyang Technological University), Jayne E. Thompson (Centre for Quantum Technologies, National University of Singapore), Xianshu Luo, X. H. Zhou (Tsinghua University), Limin Xiao (Fudan University), Weifang Huang (Chinese Academy of Sciences, Suzhou Institute of Nano-tech and Nano-bionics), L. Patrick, Mile Gu (Nanyang Technological University), L. C. Kwek (Centre for Quantum Technologies, National University of Singapore), A. Q. Liu (Nanyang Technological University)

Nature Communications
License: CC BY

Abstract: Abstract Large-scale, highly integrated and low-power-consuming hardware is becoming progressively more important for realizing optical neural networks (ONNs) capable of advanced optical computing. Traditional experimental implementations need N 2 units such as Mach-Zehnder interferometers (MZIs) for an input dimension N to realize typical computing operations (convolutions and matrix multiplication), resulting in limited scalability and consuming excessive power. Here, we propose the integrated diffractive optical network for implementing parallel Fourier transforms, convolution operations and application-specific optical computing using two ultracompact diffractive cells (Fourier transform operation) and only N MZIs. The footprint and energy consumption scales linearly with the input data dimension, instead of the quadratic scaling in the traditional ONN framework. A ~10-fold reduction in both footprint and energy consumption, as well as equal high accuracy with previous MZI-based ONNs was experimentally achieved for computations performed on the MNIST and Fashion-MNIST datasets. The integrated diffractive optical network (IDNN) chip demonstrates a promising avenue towards scalable and low-power-consumption optical computational chips for optical-artificial-intelligence.

Published on 24 Feb. 2022