A Fast Evolutionary Learning to Optimize CNN. Issue 6 (1st November 2020)

• Record Type: Journal Article
• Authors: Chen, Jinyin; Lin, Xiang; Gao, Shangtengda; Xiong, Hui; Zhang, Longyuan; Liu, Yi; Xuan, Qi
• Is Part Of: Chinese journal of electronics. Volume 29:Issue 6(2020)
• Page Start: 1061
• Page End: 1073
• Publication Date: 2020-11-01
• Subjects: convolutional neural nets -- genetic algorithms -- learning (artificial intelligence) -- neural net architecture; optimize CNN -- deep neural networks -- convolutional neural network -- DNN -- diverse tasks -- CNN model -- practical task -- architecture optimization -- optimization problem -- genetic network programming -- GNP‐FEL -- diverse network structures -- network parameters -- multiobjective optimization -- structure compactness -- offspring CNN models -- CNN classifier -- state‐ofthe‐art CNN model -- fast evolutionary learning; Evolutionary learning -- Genetic network programming (GNP) -- CNN -- Multi‐objective optimization -- Incremental training; Electronics -- Periodicals; Electronics -- China -- Periodicals; Electronics; China; Periodicals; 621.38105
• DOI: 10.1049/cje.2020.09.007
• Languages: English
• ISSNs: 1022-4653

Abstract

Abstract : Deep neural networks (DNNs) show great performance in lots of applications. Convolutional neural network (CNN) is one of the classic DNNs, and various modified CNNs have been brought up, such as DenseNet, GoogleNet, ResNet, etc. For diverse tasks, a unique structure of CNN may show its advantage. However, how to design an effective CNN model for a practical task is a puzzle. In this paper, we model the architecture optimization of CNN as an optimization problem and design a Genetic network programming based Fast evolutionary learning (GNP‐FEL) to optimize CNN. GNP‐FEL contains three main ideas: First GNP is adopted to optimize CNN architecture and hyperparameters, which can build diverse network structures and make network parameters selfevolve; Second multi‐objective optimization is designed by balancing both CNN model efficiency and structure compactness; Last a novel incremental training method is proposed to train offspring CNN models in GNP, which is capable of reducing time complexity sharply. Experiments have validated that GNP‐FEL can quickly evolve a CNN classifier with a sufficiently compact architecture. And the classifier has a comparable classification effect to state‐oftheart CNN model.