摘要
We propose an optical tensor core(OTC) architecture for neural network training. The key computational components of the OTC are the arrayed optical dot-product units(DPUs). The homodyne-detection-based DPUs can conduct the essential computational work of neural network training, i.e., matrix-matrix multiplication. Dual-layer waveguide topology is adopted to feed data into these DPUs with ultra-low insertion loss and cross talk. Therefore, the OTC architecture allows a large-scale dot-product array and can be integrated into a photonic chip. The feasibility of the OTC and its effectiveness on neural network training are verified with numerical simulations.
作者
Shaofu Xu
Weiwen Zou
徐绍夫;邹卫文(State Key Laboratory of Advanced Optical Communication Systems and Networks,Intelligent Microwave Lightwave Integration Innovation Center,Department of Electronic Engineering,Shanghai Jiao Tong University,Shanghai 200240,China)
基金
supported by the National Key R&D Program of China (No.2019YFB2203700)
the National Natural Science Foundation of China (No.61822508)。
