Evolutionary approximation and neural architecture search

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

@Article{Pinos:2022:GPEM,

• author = "Michal Pinos and Vojtech Mrazek and Lukas Sekanina",
• title = "Evolutionary approximation and neural architecture search",
• journal = "Genetic Programming and Evolvable Machines",
• year = "2022",
• volume = "23",
• number = "3",
• pages = "351--374",
• month = sep,
• note = "Special Issue: Highlights of Genetic Programming 2021 Events",
• keywords = "genetic algorithms, genetic programming, Cartesian genetic programming, Approximate computing, Convolutional neural network, ANN, Neuroevolution, Energy efficiency",
• ISSN = "1389-2576",
• DOI = "doi:10.1007/s10710-022-09441-z",
• size = "24 pages",
• abstract = "Automated neural architecture search (NAS) methods are now employed to routinely deliver high-quality neural network architectures for various challenging data sets and reduce the designers effort. The NAS methods using multi-objective evolutionary algorithms are especially useful when the objective is not only to minimize the network error but also to reduce the number of parameters (weights) or power consumption of the inference phase. We propose a multiobjective NAS method based on Cartesian genetic programming for evolving convolutional neural networks (CNN). The method allows approximate operations to be used in CNNs to reduce the power consumption of a target hardware implementation. During the NAS process, a suitable CNN architecture is evolved together with selecting approximate multipliers to deliver the best trade-offs between accuracy, network size, and power consumption. The most suitable 8 by N-bit approximate multipliers are automatically selected from a library of approximate multipliers. Evolved CNNs are compared with CNNs developed by other NAS methods on the CIFAR-10 and SVHN benchmark problems.",
• notes = "Faculty of Information Technology, Brno University of Technology, Brno, Czech Republic",

}

Genetic Programming entries for Michal Pinos Vojtech Mrazek Lukas Sekanina

Citations