Affiliation:
1. Aichi Institute of Technology
2. Toyota Technological Institute
Abstract
We propose a magneto-optical diffractive deep neural network (MO-D2NN). We simulated several MO-D2NNs, each of which consists of five hidden layers made of a magnetic material that contains 100 × 100 magnetic domains with a domain width of 1 µm and an interlayer distance of 0.7 mm. The networks demonstrate a classification accuracy of > 90% for the MNIST dataset when light intensity is used as the classification measure. Moreover, an accuracy of > 80% is obtained even for a small Faraday rotation angle of π/100 rad when the angle of polarization is used as the classification measure. The MO-D2NN allows the hidden layers to be rewritten, which is not possible with previous implementations of D2NNs.
Subject
Atomic and Molecular Physics, and Optics
Cited by
6 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. 光・熱・電気と磁気の相互作用を利用した新機能創成;IEEJ Transactions on Fundamentals and Materials;2024-01-01
2. Development of Fabrication Techniques for Magneto-Optical Diffractive Deep Neural Networks;IEEE Transactions on Magnetics;2023-11
3. Review of diffractive deep neural networks;Journal of the Optical Society of America B;2023-10-27
4. Development of Magneto-Optical Diffractive Deep Neural Network;2023 IEEE International Magnetic Conference - Short Papers (INTERMAG Short Papers);2023-05
5. Optical Neural Network in Free-Space and Nanophotonics;IEEE Access;2023