正规化(语言学)
人工神经网络
计算机科学
感知器
算法
微波食品加热
符号
人工智能
数学
电信
算术
作者
Weicong Na,Ke Liu,Wanrong Zhang,Feng Feng,Hongyun Xie,Dongyue Jin
出处
期刊:IEEE Microwave and Wireless Components Letters
[Institute of Electrical and Electronics Engineers]
日期:2022-07-01
卷期号:32 (7): 815-818
被引量:2
标识
DOI:10.1109/lmwc.2022.3153058
摘要
Artificial neural network (ANN) model development for microwave components principally includes two parts of work, i.e., data sampling and model structure adaptation. In existing various ANN modeling methods, the model structure adaptation process mainly focuses on adjusting the number of neurons within each hidden layer of ANN while keeping the number of layers unchanged. To make the ANN modeling process more flexible and efficient, an automated multilayer neural network structure adaptation method with $ {l_{1}}$ regularization is proposed in this letter. We propose a new ANN model structure combining multilayer perceptron (MLP) and additional connections between the output layer and each hidden layer/input layer. A new training scheme with $ {l_{1}}$ regularization is proposed to automatically determine the final model structure with user-desired model accuracy. Using the proposed model structure adaptation method, both the number of layers and the number of neurons within each layer of the final ANN model can be adaptively determined to address different needs for different microwave modeling problems. The proposed method is demonstrated by two microwave filter modeling examples in which the model development process achieves a time saving of at least 40% over existing methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI