Open AccessOptimal Design of Deep Residual Network Based on Image Classification of Fashion-MNIST Dataset
Author(s) -
Yusi Tang,
Han-guo Cui,
Shuyong Liu
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1624/5/052011
Subject(s) - mnist database , residual , artificial neural network , computer science , artificial intelligence , convergence (economics) , deep learning , process (computing) , image (mathematics) , network architecture , network model , machine learning , pattern recognition (psychology) , data mining , algorithm , computer security , economics , economic growth , operating system
With the increasing number of layers of deep neural network, the performance of the model tends to be saturated gradually. As a very deep network architecture, the deep residual network shows beneficial characteristics in precision and convergence. This paper deeply studied the essence of deep residual network and intended to design an optimal model for classification in Fashion-MNIST dataset. Due to the significant effects of the hyper-parameters in neural network models, the method of designing model structure and optimizing training process were investigated. Next, the performances of the training models under different conditions were compared, and finally an optimal training model whose accuracy was up to 96.21% was obtained. The experimental result shows that the performance of the model can be improved by partly widening the network and selecting more advanced training process.