Abstract
The convolution neural network (CNN) is a classical neural network with advantages in image processing. The use of multiport optical interferometric linear structures in neural networks has recently attracted a great deal of attention. Here, we use three 3 × 3 reconfigurable optical processors, based on Mach-Zehnder interferometers (MZIs), to implement a two-layer CNN. To circumvent the random phase errors originating from the fabrication process, MZIs are calibrated before the classification experiment. The MNIST datasets and Fashion-MNIST datasets are used to verify the classification accuracy. The optical processor achieves 86.9% accuracy on the MNIST datasets and 79.3% accuracy on the Fashion-MNIST datasets. Experiments show that we can improve the classification accuracy by reducing phase errors of MZIs and photodetector (PD) noises. In the future, our work provides a way to embed the optical processor in CNN to compute matrix multiplication.
Highlights
The computing power of state-of-the-art Artificial Intelligence (AI) equipment increases gradually
In 2018, Bagherian et al proposed the concept of an all-optical convolution neural network (CNN) based on an Mach-Zehnder interferometers (MZIs)-based nanophotonic circuit, which reduces a fraction of energy compared to state-of-the-art electronic devices [4]
This paper presents a programming process of three 3 × 3 reconfigurable MZI-based optical processors to implement fast and energy-efficient multiplication and addition calculations (MAC) deployed on a two-layer
Summary
The computing power of state-of-the-art Artificial Intelligence (AI) equipment increases gradually (doubling every 3.5 months on average). Due to the inherent parallelism of optics, the silicon photonic device is a promising optimization platform for linear multiplication and addition calculations (MAC) to reduce computation time from O(N2 ) to. In 2017, Shen et al proposed an integrated and programmable MZI-based nanophotonic circuit to realize MAC of electrical fully connected neural networks, and its accuracy is 76.7% [3]. In 2018, Bagherian et al proposed the concept of an all-optical CNN based on an MZI-based nanophotonic circuit, which reduces a fraction of energy compared to state-of-the-art electronic devices [4]. In 2019, Shokraneh et al implemented a 4 × 4 MZI-based optical processor used in a single-layer neural network [5]. This paper presents a programming process of three 3 × 3 reconfigurable MZI-based optical processors to implement fast and energy-efficient MAC deployed on a two-layer.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
