%0 Journal Article
%A GUO Mingxiao
%A WANG Hongwei
%A WANG Jia
%A LI Haozhe
%A YANG Shiqi
%T Convolutional Neural Network Optimization Method Based on Momentum Fractional Order Gradient Descent Algorithm
%D 2022
%R 10.3778/j.issn.1002-8331.2103-0118
%J Computer Engineering and Applications
%P 80-87
%V 58
%N 6
%X Aiming at the slow convergence speed of convolutional neural network trained by traditional gradient descent algorithm, a momentum fractional order gradient descent algorithm is proposed. The definition of fractional order calculus is introduced, and according to the problem description, the momentum thought of integer order gradient descent algorithm is applied to the fractional order gradient descent algorithm through algorithm derivation, then the momentum fractional order gradient descent algorithm is designed. The convergence of the algorithm is verified by using the test function, and the influence of different fractional orders and momentum coefficients on the algorithm are analyzed. The momentum fractional order gradient descent algorithm is used to compare with the traditional gradient descent algorithm and momentum gradient descent algorithm on three datasets. The experimental data shows that the momentum fractional order gradient descent algorithm can greatly improve the convergence speed of convolutional neural network on datasets with different complexity levels, while ensuring high classification accuracy, and saving a lot of training time.卷积神经网络；分数阶；梯度下降；动量
%U http://cea.ceaj.org/EN/10.3778/j.issn.1002-8331.2103-0118