Affiliations: [a]
School of Mathematics and Statistics, Guizhou University, Guiyang, China
| [b]
School of Mathematics and Statistics, Central South University, Changsha, China
| [c]
High-tech Research Institute, Hunan Institute of Traffic Engineering, Hengyang, China
| [d]
School of Civil Engineering, Changsha University of Science and Technology, Changsha, China
Correspondence:
[*]
Corresponding author. Muzhou Hou, School of Mathematics and Statistics, Central South University, Changsha 410083, China. E-mail: [email protected].
Abstract: In this paper, block neural network (BNN) method is proposed to solve several kinds of differential equations. BNN is used to construct approximating functions and its derivatives, the improved extreme learning machine (IELM) algorithm are designed to train network weights. To evaluate the performance of the proposed method, numerical examples are performed by the presented method. Comparison of the numerical results with exact solutions validate the feasibility of the proposed method in accuracy. Results compared with other recent research works also validate the superiority of the proposed approach. Numerical results show that the proposed BNN with IELM algorithm perform well in accuracy and requires less hidden neurons.
