Neural Architecture Search based on Cartesian Genetic Programming Coding Method

Created by W.Langdon from gp-bibliography.bib Revision:1.7630

@Misc{DBLP:journals/corr/abs-2103-07173,

• author = "Xuan Wu and Xiuyi Zhang and Linhan Jia and Liang Chen and Yanchun Liang and You Zhou and Chunguo Wu",
• title = "Neural Architecture Search based on Cartesian Genetic Programming Coding Method",
• howpublished = "arXiv",
• volume = "abs/2103.07173",
• year = "2021",
• month = "28 " # sep,
• keywords = "genetic algorithms, genetic programming, Cartesian Genetic Programming, ANN, Neural architecture search, Attention mechanism, Sentence classification",
• URL = "https://arxiv.org/abs/2103.07173",
• eprinttype = "arXiv",
• eprint = "2103.07173",
• timestamp = "Thu, 30 Sep 2021 01:00:00 +0200",
• biburl = "https://dblp.org/rec/journals/corr/abs-2103-07173.bib",
• bibsource = "dblp computer science bibliography, https://dblp.org",
• size = "11 pages",
• abstract = "Neural architecture search (NAS) is a hot topic in the field of automated machine learning and outperforms humans in designing neural architectures on quite a few machine learning tasks. Motivated by the natural representation form of neural networks by the Cartesian genetic programming (CGP), we propose an evolutionary approach of NAS based on CGP, called CGPNAS, to solve sentence classification task. To evolve the architectures under the framework of CGP, the operations such as convolution are identified as the types of function nodes of CGP, and the evolutionary operations are designed based on Evolutionary Strategy. The experimental results show that the searched architectures are comparable with the performance of human-designed architectures. We verify the ability of domain transfer of our evolved architectures. The transfer experimental results show that the accuracy deterioration is lower than 2-5%. Finally, the ablation study identifies the Attention function as the single key function node and the linear transformations along could keep the accuracy similar with the full evolved architectures, which is worthy of investigation in the future.",
• notes = "See \cite{Wu_Xuan:ieeeTEC}",

}

Genetic Programming entries for Xuan Wu Xiuyi Zhang Linhan Jia Liang Chen Yanchun Liang You Zhou Chunguo Wu

Citations