计算机科学
人工神经网络
相(物质)
化学
人工智能
有机化学
作者
Qiaomu Hu,Chu Wu,Jingyu Zhao,Rui Zeng,Shuang Zheng,Minming Zhang
标识
DOI:10.1364/cleo_si.2024.sf2m.5
摘要
We propose a non-volatile reconfigurable digital all-optical diffractive neural network based on Sb 2 Se 3 phase-change material. With three optical diffraction layers and a correcting layer, our model achieves 94.46% accuracy for handwritten digit recognition.
科研通智能强力驱动
Strongly Powered by AbleSci AI