arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1809.08360cs.LGstat.ML
收藏

对“使用衍射深度神经网络的全光学机器学习“的评论

Comment on "All-optical machine learning using diffractive deep neural networks"

Ambow Research Institute, Ambow Education Group(安博教育集团安博研究院);The Third Affiliated Hospital of Sun Yat-sen University(中山大学附属第三医院);Texas A&M University(得克萨斯农工大学)

Haiqing Wei, Gang Huang, Xiuqing Wei, Yanlong Sun, Hongbin Wang

摘要:

Lin等人(报告,2018年9月7日,第1004页)报告了一项引人注目的提议,该提议采用无源、严格线性的光学设置来执行模式分类。但是,将多层衍射设置解释为深度神经网络并将其倡导为全光学深度学习框架并不合理,并且通过忽视其完美线性和严格无源性的定义特征来代表对系统的错误描述。

英文摘要:

Lin et al. (Reports, 7 September 2018, p. 1004) reported a remarkable proposal that employs a passive, strictly linear optical setup to perform pattern classifications. But interpreting the multilayer diffractive setup as a deep neural network and advocating it as an all-optical deep learning framework are not well justified and represent a mischaracterization of the system by overlooking its defining characteristics of perfect linearity and strict passivity.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑