A Survey on Evolutionary Neural Architecture Search

• Published in: IEEE transaction on neural networks and learning systems Vol. 34; no. 2; pp. 550 - 570
• Main Authors: Liu, Yuqiao, Sun, Yanan, Xue, Bing, Zhang, Mengjie, Yen, Gary G., Tan, Kay Chen
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.02.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Artificial neural networks; Computer architecture; Convolutional neural networks; Deep learning; Design; Evolutionary computation; evolutionary computation (EC); evolutionary neural architecture search (NAS); image classification; Neural networks; Optimization; Search problems; Statistics
• ISSN: 2162-237X; 2162-2388; 2162-2388
• DOI: 10.1109/TNNLS.2021.3100554

Deep neural networks (DNNs) have achieved great success in many applications. The architectures of DNNs play a crucial role in their performance, which is usually manually designed with rich expertise. However, such a design process is labor-intensive because of the trial-and-error process and also not easy to realize due to the rare expertise in practice. Neural architecture search (NAS) is a type of technology that can design the architectures automatically. Among different methods to realize NAS, the evolutionary computation (EC) methods have recently gained much attention and success. Unfortunately, there has not yet been a comprehensive summary of the EC-based NAS algorithms. This article reviews over 200 articles of most recent EC-based NAS methods in light of the core components, to systematically discuss their design principles and justifications on the design. Furthermore, current challenges and issues are also discussed to identify future research in this emerging field.