Correlation Analysis-Based Neural Network Self-Organizing Genetic Evolutionary Algorithm

• Published in: IEEE access Vol. 7; pp. 135099 - 135117
• Main Authors: Chai, Zenghao, Yang, Xu, Liu, Zhilin, Lei, Yunlin, Zheng, Wenhao, Ji, Mengyao, Zhao, Jinfeng
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial intelligence; Artificial neural networks; Biological neural networks; Correlation; Correlation analysis; Evolution (biology); Evolutionary algorithms; Evolutionary computation; Genetic algorithms; neural evolution; neural network; Neural networks; Neurons; optimization; Redundant components; Synapses; Training
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2942035

Recent years, there has been an ever increasing interest and investment on Artificial Intelligence (AI), both academic and industrial. As the hotspots in AI, Artificial Neural Networks (ANNs) have already been applied to a lot of different applications. However, traditional ANNs have disadvantages, such as fixed and redundant structure, resulting in requirement of large amount of training data and training time. Biological researches have shown that the biological neural network behaves in a more flexible way, with synapses building or withering according to requirement. In this paper, we present a Correlation Analysis Based Neural Network Self-Organizing Genetic Evolutionary Algorithm. Based on correlation analysis of training process, self-organizing combined with genetic evolutionary algorithm is applied to improve the performance efficiency and structural efficiency of the built neural network. Results show that our algorithm could generate neural networks with more compact structure and reasonable classification accuracy.