Bio computing algorithms(GA, PSO, Grey wolf, Immune computing algorithm) to tune CNN hyperparametrs using for CIFAR-10

there is no standard way to determine the architecture of a CNN. Domain knowledge and human expertise are required in order to design a CNN architecture. Typically architectures are created by experimenting and modifying a few existing networks. I want those 4 algorithms to generate successful CNN architectures for CIFAR-10. Each algorithm should be tested to generate CNN architecture on the same dataset and compare their performance. each algorithm should be tested 10 times(E.g in case of GA tested on 10 different generation).