HyperEstimator: Evolving Computationally Efficient CNN Models with Grammatical Evolution

Created by W.Langdon from gp-bibliography.bib Revision:1.8194

@InProceedings{Vaidya:2022:ICSBT,

• author = "Gauri Vaidya and Luise Ilg and Meghana Kshirsagar and Enrique Naredo and Conor Ryan",
• title = "HyperEstimator: Evolving Computationally Efficient {CNN} Models with Grammatical Evolution",
• booktitle = "Proceedings of the 19th International Conference on Smart Business Technologies (ICSBT 2022)",
• year = "2022",
• editor = "Fons Wijnhoven and Slimane Hammoudi and Marten {van Sinderen}",
• pages = "57--68",
• address = "Lisbon, Portugal",
• organization = "INSTICC",
• publisher = "SciTePress",
• keywords = "genetic algorithms, genetic programming, Grammatical Evolution, ANN, deep learning, Convolutional Neural Networks, Grammatical Evolution, Machine Learning, GPU, Business Modelling, Hyperparameters, Smart City",
• isbn13 = "978-989-758-587-6",
• ISSN = "2184-772X",
• URL = "https://pure.ul.ie/en/publications/hyperestimator-evolving-computationally-efficient-cnn-models-with",
• DOI = "doi:10.5220/0011324800003280",
• size = "12 pages",
• abstract = "... dramatically leading to massive project costs. Some of the factors for vast expenses for DL models can be attributed to the computational costs incurred during training, massive storage requirements, along with specialized hardware such as Graphical Processing Unit (GPUs). This research seeks to address some of the challenges mentioned above. Our approach, HyperEstimator, estimates the optimal values of hyperparameters for a given Convolutional Neural Networks (CNN) model and dataset using a suite of Machine Learning algorithms. Our approach consists of three stages: (i) obtaining c andidate values for hyperparameters with Grammatical Evolution; (ii) prediction of optimal values of hyperparameters with supervised ML techniques; (iii) training CNN model for object detection. As a case study, the CNN models are validated by using a real-time video dataset representing road traffic captured in some Indian cities. The results are also compared against CIFAR10 and CIFAR100 benchmark datasets.",
• notes = "also known as \cite{icsbt22}",

}

Genetic Programming entries for Gauri Vaidya Luise Ilg Meghana Kshirsagar Enrique Naredo Conor Ryan

Citations