Convolutional neural networks with fractional order gradient method

NEUROCOMPUTING

卷:408

Article

Sheng, Dian¹  Wei, Yiheng¹  Chen, Yuquan¹  Wang, Yong¹ 

[1] Univ Sci & Technol China, Dept Automat, Hefei 230026, Peoples R China

关键词: Fractional order calculus;    Gradient method;    Neural networks;    Backward propagation;   

DOI  :  10.1016/j.neucom.2019.10.017

来源: Elsevier

【 摘 要 】

This paper proposes a fractional order gradient method for the backward propagation of convolutional neural networks. To overcome the problem that fractional order gradient method cannot converge to real extreme point, a simplified fractional order gradient method is designed based on Caputo's definition. The parameters within layers are updated by the designed gradient method, but the propagations between layers still use integer order gradients, and thus the complicated derivatives of composite functions are avoided and the chain rule will be kept. By connecting every layers in series and adding loss functions, the proposed convolutional neural networks can be trained smoothly according to various tasks. Some practical experiments are carried out in order to demonstrate fast convergence, high accuracy and ability to escape local optimal point at last. (C) 2019 Elsevier B.V. All rights reserved.

【 授权许可】

Free