An adaptive and modular framework for evolving deep neural networks

Santos, F. J. J. B., Gonçalves, I., & Castelli, M. (2023). Neuroevolution with box mutation: An adaptive and modular framework for evolving deep neural networks. Applied Soft Computing, 147(November), 1-15. [110767]. https://doi.org/10.1016/j.asoc.2023.110767 --- Funding: This work is funded by national funds through the FCT - Foundation for Science and Technology, I.P., within the scope of the projects CISUC - UID/CEC/00326/2020, UIDB/04152/2020 - Centro de Investigação em Gestão de Informação (MagIC)/NOVA IMS, and by European Social Fund, through the Regional Operational Program Centro 2020 .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 89% 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.publishersversionpublishe