Circuit Connectivity Inspired Neural Network for Analog Mixed-Signal Functional Modeling
Circuit Connectivity Inspired Neural Network for Analog Mixed-Signal Functional Modeling
复制标题
受电路连接启发的神经网络用于模拟混合信号功能建模
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
M. Chen
中科院分区：
文献类型：
--
作者：
Mohsen Hassanpourghadi;Shiyu Su;Rezwan A. Rasul;Juzheng Liu;Qiaochu Zhang;M. Chen
在模拟/混合信号（AMS）电路的各种回归方法中，人工神经网络（ANN）因其合理的精度和快速的评估而成为一个有前途的候选方法。然而，对于具有宽规格范围的复杂AMS电路，创建人工神经网络模型需要大量的训练数据集。为了减少所需训练数据集的体积，我们提出了一种电路连接启发的神经网络（CCI-NN），其中包括根据实际电路连接连接的多个子神经网络。为了验证，我们使用CCI-NN对三级放大器和电流转向数模转换器进行了建模。在一定的建模精度下，训练数据集需求降低了3.5 -7.6倍。
Among different types of regression methods to model Analog/Mixed-Signal (AMS) circuits, the Artificial Neural Network (ANN) is a promising candidate due to its reasonable accuracy and fast evaluation. However, for complex AMS circuits with wide specification ranges, creating an ANN model requires a large training dataset. To reduce the required training dataset’s volume, we have proposed a circuit-connectivity-inspired ANN (CCI-NN), including multiple sub-ANNs linked according to the actual circuit connections. For validation, we have employed CCI-NN to model a three-stage amplifier and a current-steering digital-to-analog converter. For a certain modeling accuracy, the training dataset requirement is reduced by 3.5x-7.6x.