Grammatical Evolution-Driven Algorithm for Efficient and Automatic Hyperparameter Optimisation of Neural Networks

Created by W.Langdon from gp-bibliography.bib Revision:1.8229

@Article{Vaidya:2023:Algorithms,

• author = "Gauri Vaidya and Meghana Kshirsagar and Conor Ryan",
• title = "Grammatical Evolution-Driven Algorithm for Efficient and Automatic Hyperparameter Optimisation of Neural Networks",
• journal = "Algorithms",
• year = "2023",
• volume = "16",
• number = "7",
• pages = "article number 319",
• keywords = "genetic algorithms, genetic programming, Grammatical Evolution, ANN, search space pruning, machine learning, combinatorial optimisation, computer vision, metaheuristics, hyperparameter tuning, deep learning, neural networks",
• ISSN = "1999-4893",
• URL = "https://www.mdpi.com/1999-4893/16/7/319",
• DOI = "doi:10.3390/a16070319",
• size = "16 pages",
• abstract = "... Neural networks have revolutionised the way we approach problem solving across multiple domains; however, their effective design and efficient use of computational resources is still a challenging task. One of the most important factors influencing this process is model hyperparameters which vary significantly with models and datasets. Recently, there has been an increased focus on automatically tuning these hyperparameters to reduce complexity and to optimise resources. From traditional human-intuitive tuning methods to random search, grid search, Bayesian optimisation, and evolutionary algorithms, significant advancements have been made in this direction that promise improved performance while using fewer resources. we propose HyperGE, a two-stage model for automatically tuning hyperparameters driven by grammatical evolution (GE), a bioinspired population-based machine learning algorithm. GE provides an advantage in that it allows users to define their own grammar for generating solutions, making it ideal for defining search spaces across datasets and models. We test HyperGE to fine-tune VGG-19 and ResNet-50 pre-trained networks using three benchmark datasets. We demonstrate that the search space is significantly reduced by a factor of about ninty percent Stage 2 with fewer number of trials. HyperGE could become an invaluable tool within the deep learning community, allowing practitioners greater freedom when exploring complex problem domains for hyperparameter fine-tuning.",
• notes = "also known as \cite{a16070319}",

}

Genetic Programming entries for Gauri Vaidya Meghana Kshirsagar Conor Ryan

Citations