A Grammar-based Genetic Programming Approach to Optimize Convolutional Neural Network Architectures

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

@InProceedings{Barbosa-Diniz:2018:eniac,

• author = "Jessica {Barbosa Diniz} and Filipe R. Cordeiro and Pericles B. C. Miranda and Laura A. {Tomaz da Silva}",
• title = "A Grammar-based Genetic Programming Approach to Optimize Convolutional Neural Network Architectures",
• booktitle = "Anais do XV Encontro Nacional de Inteligencia Artificial e Computacional",
• year = "2018",
• editor = "Denis D. Maua and Murilo Naldi",
• pages = "82--93",
• address = "Sao Paulo, Brazil",
• publisher_address = "Porto Alegre, RS, Brasil",
• month = "22-25 " # oct,
• publisher = "Sociedade Brasileira de Computacao",
• keywords = "genetic algorithms, genetic programming, Grammatical Evolution, PonyGE2, ANN, CNN, Keras, image processing",
• URL = "https://sol.sbc.org.br/index.php/eniac/article/view/4406",
• URL = "https://sol.sbc.org.br/index.php/eniac/article/view/4406/4330.pdf",
• DOI = "doi:10.5753/eniac.2018.4406",
• size = "12 pages",
• abstract = "Deep Learning is a research area under the spotlight in recent years due to its successful application to many domains, such as computer vision and image recognition. The most prominent technique derived from Deep Learning is Convolutional Neural Network, which allows the network to automatically learn representations needed for detection or classification tasks. However, Convolutional Neural Networks have some limitations, as designing these networks are not easy to master and require expertise and insight. In this work, we present the use of Genetic Algorithm associated to Grammar-based Genetic Programming to optimize Convolution Neural Network architectures. To evaluate our proposed approach, we adopted CIFAR-10 dataset to validate the evolution of the generated architectures, using the metric of accuracy to evaluate its classification performance in the test dataset. The results demonstrate that our method using Grammar-based Genetic Programming can easily produce optimized CNN architectures that are competitive and achieve high accuracy results.",
• notes = "Federal Rural University of Pernambuco (UFRPE), Brazil",

}

Genetic Programming entries for Jessica Barbosa Diniz Filipe Rolim Cordeiro Pericles Barbosa Miranda Laura Angelica Tomaz da Silva

Citations