Auto-DenseNet: DenseNet Optimization Method Based on Evolutionary Algorithm

Leilei Zhai, Dianwei Wang, Jie Fang, Zhijie Xu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


To address the issue of time-consuming and laborious design of network structure parameters and connection methods, in this paper we propose an evolutionary algorithm-based DenseNet network optimization method (Auto Dense Convolutional Network, Auto-DenseNet). Firstly, the internal parameters of DenseNet are encoded to generate an initial population, and crossover and variation operators are designed to ensure the effectiveness of the evolution of offspring. Secondly, the dataset is imported into the decoded individual evaluation fitness. And then, the superior individuals are selected to enter the next iteration. Finally, the optimized network individuals are selected for the image classification task. After tuning validation on the MNIST-RD dataset, tests were conducted on three widely used benchmark image classification datasets. The experimental results demonstrate that the network structure searched by the Auto-DenseNet algorithm outperforms most existing structures in terms of classification performance, and the number of network parameters.

Original languageEnglish
Title of host publication5th International Conference on Intelligent Autonomous Systems, ICoIAS 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages7
ISBN (Electronic)9781665498388, 9781665498371
ISBN (Print)9781665498395
Publication statusPublished - 8 Nov 2022
Event5th International Conference on Intelligent Autonomous Systems - Dalian, China
Duration: 23 Sep 202225 Sep 2022
Conference number: 5


Conference5th International Conference on Intelligent Autonomous Systems
Abbreviated titleICoIAS 2022


Dive into the research topics of 'Auto-DenseNet: DenseNet Optimization Method Based on Evolutionary Algorithm'. Together they form a unique fingerprint.

Cite this