|
| 光学全连接神经网络与光学卷积神经网络的仿真分析 |
| Simulation and analysis of optical fully connected neural networks and optical convolutional neural networks |
| 投稿时间：2024-01-28 |
| DOI：10.3969/j.issn.1005-5630.202401280012 |
| 中文关键词: 光学全连接神经网络 光学卷积神经网络 马赫-曾德尔干涉仪 |
| 英文关键词:optical fully connected neural network optical convolutional neural network Mach-Zehnder interferometer |
| 基金项目:国家重点研发计划（2021YFB2802300） |
|
| 摘要点击次数: 1667 |
| 全文下载次数: 1060 |
| 中文摘要: |
| 光学神经网络作为下一代人工神经网络，具有高速度和低功耗的优点。针对目前正在发展的光学神经网络，对由相互连接的马赫-曾德尔干涉仪构成的光学全连接神经网络与光学卷积神经网络进行研究。介绍了两种光学神经网络在算法和结构上的特点与实现方式。利用pytorch和INTERCONNECT软件，对两种光学神经网络进行了仿真分析，分别从图像识别准确率、网络复杂度和能耗3个方面对两种光学神经网络的性能进行了对比，从而阐明了光学全连接神经网络与光学卷积神经网络各自的优缺点，为以后光学神经网络的发展提供借鉴。 |
| 英文摘要: |
| Optical neural networks, as the next generation of artificial neural networks, have the advantages of high speed and low power consumption. Optical fully connected neural networks and optical convolutional neural networks consisting of interconnected Mach–Zehnder interferometer were investigated with respect to optical neural networks currently under development. The characteristics and implementations of two optical neural networks in terms of algorithms and structures were presented. Using pytorch and INTERCONNECT software, two kinds of optical neural networks were simulated and analyzed, and the performance of the two kinds of optical neural networks were compared in terms of image recognition accuracy, network complexity, and energy consumption, so as to elucidate the advantages and disadvantages of each of the optical fully-connected neural networks and the optical convolutional neural networks, and to provide reference for the development of optical neural networks in the future. |
| HTML 查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |
