A Genetic Programming Approach to Designing Convolutional Neural Network Architectures

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

@InProceedings{Suganuma:2018:IJCAI,

• author = "Masanori Suganuma and Shinichi Shirakawa and Tomoharu Nagao",
• title = "A Genetic Programming Approach to Designing Convolutional Neural Network Architectures",
• booktitle = "Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, {IJCAI-18}",
• year = "2018",
• editor = "Jerome Lang",
• pages = "5369--5373",
• month = "13-19 " # jul,
• publisher = "International Joint Conferences on Artificial Intelligence Organization",
• keywords = "genetic algorithms, genetic programming, Cartesian genetic programming, ANN, Machine Learning: Classification, Neural Networks, Deep Learning",
• isbn13 = "978-0-9992411-2-7",
• DOI = "doi:10.24963/ijcai.2018/755",
• URL = "https://doi.org/10.24963/ijcai.2018/755",
• size = "5 pages",
• abstract = "We propose a method for designing convolutional neural network (CNN) architectures based on Cartesian genetic programming (CGP). In the proposed method, the architectures of CNNs are represented by directed acyclic graphs, in which each node represents highly-functional modules such as convolutional blocks and tensor operations, and each edge represents the connectivity of layers. The architecture is optimised to maximize the classification accuracy for a validation dataset by an evolutionary algorithm. We show that the proposed method can find competitive CNN architectures compared with state-of-the-art methods on the image classification",
• notes = "RIKEN Center for AIP",

}

Genetic Programming entries for Masanori Suganuma Shinichi Shirakawa Tomoharu Nagao

Citations