Neuroevolution with box mutation: An adaptive and modular framework for evolving deep neural networks

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@Article{SANTOS:2023:asoc,

• author = "Frederico J. J. B. Santos and Ivo Goncalves and Mauro Castelli",
• title = "Neuroevolution with box mutation: An adaptive and modular framework for evolving deep neural networks",
• journal = "Applied Soft Computing",
• volume = "147",
• pages = "110767",
• year = "2023",
• ISSN = "1568-4946",
• DOI = "doi:10.1016/j.asoc.2023.110767",
• URL = "https://www.sciencedirect.com/science/article/pii/S1568494623007858",
• keywords = "genetic algorithms, genetic programming, Neuroevolution, ANN, Evolutionary deep learning, Neural architecture search, Supervised learning",
• abstract = "The pursuit of self-evolving neural networks has driven the emerging field of Evolutionary Deep Learning, which combines the strengths of Deep Learning and Evolutionary Computation. This work presents a novel method for evolving deep neural networks by adapting the principles of Geometric Semantic Genetic Programming, a subfield of Genetic Programming, and Semantic Learning Machine. Our approach integrates evolution seamlessly through natural selection with the optimization power of backpropagation in deep learning, enabling the incremental growth of neural networks' neurons across generations. By evolving neural networks that achieve nearly 89percent accuracy on the CIFAR-10 dataset with relatively few parameters, our method demonstrates remarkable efficiency, evolving in GPU minutes compared to the field standard of GPU days",

}

Genetic Programming entries for Frederico J J B Santos Ivo Goncalves Mauro Castelli

Citations