Evolutionary neural architecture search based on evaluation correction and functional units

Neural architecture search (NAS) has been a great success in the automated design of deep neural networks. However, neural architecture search using evolutionary algorithms is challenging due to the diverse structure of neural networks and the difficulty in performance evaluation. To this end, this paper proposes an evolutionary neural architecture search algorithm (called EF-ENAS) based on evaluation corrections and functional units. First, a mating selection operation based on evaluation correction is developed, which can help EF-ENAS discriminate high-performance network architectures and reduce the harmful effects of low fidelity accuracy evaluation methods. Then, a functional unit-based network architecture crossover operation is designed, which divides the neural network into different functional units for crossover and protects valuable network architectures from destruction. Finally, the idea of species protection is introduced into the traditional environmental selection operation and a species protection-based environmental selection operation is designed, which can improve the diversity of network architectures in a population. The EF-ENAS is tested on ten benchmark datasets with varying complexities. In addition, the proposed algorithm is compared with 44 state-of-the-art algorithms, including DARTS, EvoCNN, CNN-GA, AE-CNN, etc. The experimental results show that the proposed algorithm1 can automatically design neural networks and perform better. (c) 2022 Elsevier B.V. All rights reserved.

Automated summary

This paper proposes an evolutionary neural architecture search algorithm (EF-ENAS) based on evaluation corrections and functional units. The experimental results show that the proposed algorithm can automatically design neural networks and perform better, while improving the diversity of network architectures in the population.