AnalogVNN: A fully modular framework for modeling and optimizing photonic neural networks
AnalogVNN: A fully modular framework for modeling and optimizing photonic neural networks
复制标题
DOI：
10.1063/5.0134156
复制
发表时间：
2022-10
期刊：
影响因子：
--
通讯作者：
Vivswan Shah;N. Youngblood
中科院分区：
文献类型：
--
作者：
Vivswan Shah;N. Youngblood
在本文中，我们提出了AnalogVNN，这是一个基于PyTorch的仿真框架，可以模拟光子神经网络加速器中存在的光电噪声，有限精度和信号归一化的影响。我们使用这个框架来训练和优化线性和卷积神经网络，最多有9层，参数为1.7 × 106，同时深入了解归一化、激活函数、降低的精度和噪声如何影响模拟光子神经网络的精度。通过遵循PyTorch中存在的相同层结构设计，AnalogVNN框架允许用户仅用几行代码将大多数数字神经网络模型转换为模拟模型，充分利用PyTorch提供的开源优化，深度学习和GPU加速库。
In this paper, we present AnalogVNN, a simulation framework built on PyTorch that can simulate the effects of optoelectronic noise, limited precision, and signal normalization present in photonic neural network accelerators. We use this framework to train and optimize linear and convolutional neural networks with up to nine layers and ∼1.7 × 106 parameters, while gaining insights into how normalization, activation function, reduced precision, and noise influence accuracy in analog photonic neural networks. By following the same layer structure design present in PyTorch, the AnalogVNN framework allows users to convert most digital neural network models to their analog counterparts with just a few lines of code, taking full advantage of the open-source optimization, deep learning, and GPU acceleration libraries available through PyTorch.