.png){kind=icon}
返回
Generalized robust training scheme using genetic algorithm for optical neural networks with imprecise components
.png){kind=icon}
PRE
AI
DOI：10.1364/PRJ.449570.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
One of the pressing issues for optical neural networks (ONNs) is the performance degradation introduced by parameter uncertainties in practical optical components. Hereby, we propose a novel two-step ex situ training scheme to configure phase shifts in a Mach-Zehnder-interferometer-based feedforward ONN, where a stochastic gradient descent algorithm followed by a genetic algorithm considering four types of practical imprecisions is employed. By doing so, the learning process features fast convergence and high computational efficiency, and the trained ONN is robust to varying degrees and types of imprecisions. We investigate the effectiveness of our scheme by using practical machine learning tasks including Iris and MNIST classifications, showing more than 23% accuracy improvement after training and accuracy (90.8% in an imprecise ONN with three hidden layers and 224 tunable thermal-optic phase shifters) comparable to the ideal one (92.0%). (C) 2022 Chinese Laser Press
Keyword:
PHOTONICS
SILICON
EFFICIENT
DESIGN
期刊
IF:
7.2
论文数:
2.4K
被引数:
1.3W
机构
引用论文
分享收藏Large-scale silicon quantum photonics implementing arbitrary two-qubit processing实现任意两量子位处理的大规模硅量子光子学.png)
NATURE PHOTONICS
OAAI
NATURE PHOTONICSIF32.9
OAAI分享收藏
分享收藏Photonics for artificial intelligence and neuromorphic computing用于人工智能和神经形态计算的光子学NATURE PHOTONICSOAAI
NATURE PHOTONICSIF32.9
OAAI分享收藏
查看更多内容