卷积神经网络
增采样
计算机科学
卷积(计算机科学)
计算
人工智能
光学计算
可扩展性
传输(电信)
上下文图像分类
人工神经网络
模式识别(心理学)
计算机视觉
图像(数学)
光学
算法
电信
物理
数据库
作者
Zhengqin Gu,Yesheng Gao,Xingzhao Liu
出处
期刊:Optics Express
[The Optical Society]
日期:2021-02-09
卷期号:29 (4): 5877-5877
被引量:34
摘要
Although deeper convolutional neural networks (CNNs) generally obtain better performance on classification tasks, they incur higher computation costs. To address this problem, this study proposes the optronic convolutional neural network (OPCNN) in which all computation operations are executed in optics, and data transmission and control are executed in electronics. In OPCNN, we implement convolutional layers with multi input images by the lenslet 4 f system, downsampling layers by optical-strided convolution and obtaining nonlinear activation by adjusting the camera’s curve and fully connected layers by optical dot product. The OPCNN demonstrates good performance on the classification tasks in simulations and experiments and achieves better performance than other current optical convolutional neural networks by comparison due to the more complex architecture. The scalability of OPCNN contributes to building deeper networks when facing complicated datasets.
科研通智能强力驱动
Strongly Powered by AbleSci AI