Convolutional neural networks based on fractional-order momentum for parameter training

This paper proposes a parameter training method via the fractional-order momentum for convolutional neural networks (CNNs). To update the parameters of CNNs more smoothly, the parameter training method via the fractional-order momentum is proposed based on the Gr & uuml;nwald-Letnikov (G-L) difference operation. The stochastic classical momentum (SCM) algorithm and adaptive moment (Adam) estimation algorithm are improved by replacing the integer-order difference with the fractional-order difference. Meanwhile, the linear and the nonlinear methods are discussed to adjust the fractional-order. Therefore, the proposed methods can improve the flexibility and the adaptive ability of CNN parameters. We analyze the validity of the methods by using MNIST dataset and CIFAR-10 dataset, and the experimental results show that the proposed methods can improve the recognition accuracy and the learning convergence speed of CNNs compared with the traditional SCM and Adam methods. (c) 2021 Elsevier B.V. All rights reserved.

Automated summary

This paper proposes a parameter training method via the fractional-order momentum for convolutional neural networks (CNNs), which can update parameters more smoothly and improve the flexibility and adaptive ability of CNN parameters. Experimental results demonstrate that this method can enhance the recognition accuracy and learning convergence speed of CNNs.