Hongshang Xu¹, Bei Dong^1,2,*, Xiaochang Liu¹, Xiaojun Wu^1,2

Intelligent Automation & Soft Computing, Vol.38, No.2, pp. 185-202, 2023, DOI:10.32604/iasc.2023.041177

Abstract Deep neural networks often outperform classical machine learning algorithms in solving real-world problems. However, designing better networks usually requires domain expertise and consumes significant time and computing resources. Moreover, when the task changes, the original network architecture becomes outdated and requires redesigning. Thus, Neural Architecture Search (NAS) has gained attention as an effective approach to automatically generate optimal network architectures. Most NAS methods mainly focus on achieving high performance while ignoring architectural complexity. A myriad of research has revealed that network performance and structural complexity are often positively correlated. Nevertheless, complex network structures will bring enormous computing resources. To cope… More >

Xin Liu¹, Jie Li^1,*, Jianwei Zhao², Bin Cao^2,*, Rongge Yan³, Zhihan Lyu⁴

CMES-Computer Modeling in Engineering & Sciences, Vol.139, No.1, pp. 143-185, 2024, DOI:10.32604/cmes.2023.030391

Abstract Most of the neural network architectures are based on human experience, which requires a long and tedious trial-and-error process. Neural architecture search (NAS) attempts to detect effective architectures without human intervention. Evolutionary algorithms (EAs) for NAS can find better solutions than human-designed architectures by exploring a large search space for possible architectures. Using multiobjective EAs for NAS, optimal neural architectures that meet various performance criteria can be explored and discovered efficiently. Furthermore, hardware-accelerated NAS methods can improve the efficiency of the NAS. While existing reviews have mainly focused on different strategies to complete NAS, a few studies have explored the… More > Graphic Abstract