کد مقاله کد نشریه سال انتشار مقاله انگلیسی نسخه تمام متن
6875012 1441467 2018 12 صفحه PDF دانلود رایگان
عنوان انگلیسی مقاله ISI
EvoDeep: A new evolutionary approach for automatic Deep Neural Networks parametrisation
موضوعات مرتبط
مهندسی و علوم پایه مهندسی کامپیوتر نظریه محاسباتی و ریاضیات
پیش نمایش صفحه اول مقاله
EvoDeep: A new evolutionary approach for automatic Deep Neural Networks parametrisation
چکیده انگلیسی
Deep Neural Networks (DNN) have become a powerful, and extremely popular mechanism, which has been widely used to solve problems of varied complexity, due to their ability to make models fitted to non-linear complex problems. Despite its well-known benefits, DNNs are complex learning models whose parametrisationand architecture are made usually by hand. This paper proposes a new Evolutionary Algorithm, named EvoDeep, devoted to evolve the parameters and the architecture of a DNN in order to maximise its classification accuracy, as well as maintaining a valid sequence of layers. This model is tested against a widely used dataset of handwritten digits images. The experiments performed using this dataset show that the Evolutionary Algorithm is able to select the parameters and the DNN architecture appropriately, achieving a 98.93% accuracy in the best run.
ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Journal of Parallel and Distributed Computing - Volume 117, July 2018, Pages 180-191
نویسندگان
, , , , ,