NeuroLGP-SM: Scalable Surrogate-Assisted Neuroevolution for Deep Neural Networks

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

@InProceedings{stapleton:2024:CEC,

• author = "Fergal Stapleton and Edgar Galvan",
• title = "{NeuroLGP-SM:} Scalable Surrogate-Assisted Neuroevolution for Deep Neural Networks",
• booktitle = "2024 IEEE Congress on Evolutionary Computation (CEC)",
• year = "2024",
• editor = "Bing Xue",
• address = "Yokohama, Japan",
• month = "30 " # jun # " - 5 " # jul,
• publisher = "IEEE",
• keywords = "genetic algorithms, genetic programming, Training, Support vector machines, Sociology, Semantics, Evolutionary computation, Computer architecture, Neuroevolution, Linear Genetic Programming, Surrogate-assisted Evolutionary Algorithms",
• isbn13 = "979-8-3503-0837-2",
• DOI = "doi:10.1109/CEC60901.2024.10612039",
• abstract = "Evolutionary Algorithms (EAs) play a crucial role in the architectural configuration and training of Artificial Deep Neural Networks (DNNs), a process known as neuroevolution. However, neuroevolution is hindered by its inherent computational expense, requiring multiple generations, a large population, and numerous epochs. The most computationally intensive aspect lies in evaluating the fitness function of a single candidate solution. To address this challenge, we employ Surrogate-assisted EAs (SAEAs). While a few SAEAs approaches have been proposed in neuroevolution, none have been applied to truly large DNNs due to issues like intractable information usage. In this work, drawing inspiration from Genetic Programming semantics, we use phenotypic distance vectors, outputted from DNNs, alongside Kriging Partial Least Squares (KPLS), an approach that is effective in handling these large vectors, making them suitable for search. Our proposed approach, named Neuro-Linear Genetic Programming surrogate model (NeuroLGP-SM), efficiently and accurately estimates DNN fitness without the need for complete evaluations. NeuroLGP-SM demonstrates competitive or superior results compared to 12 other methods, including NeuroLGP without SM, convolutional neural networks, support vector machines, and autoencoders. Additionally, it is worth noting that NeuroLGP-SM is 25percent more energy-efficient than its NeuroLGP counterpart. This efficiency advantage adds to the overall appeal of our proposed NeuroLGP-SM in optimising the configuration of large DNNs.",
• notes = "also known as \cite{10612039}

  WCCI 2024",

}

Genetic Programming entries for Fergal Stapleton Edgar Galvan Lopez

Citations