Journal Home Online First Current Issue Archive For Authors Journal Information 中文版

Frontiers of Information Technology & Electronic Engineering >> 2020, Volume 21, Issue 6 doi: 10.1631/FITEE.1900593

Fractional-order global optimal backpropagation machine trained by an improved fractional-order steepest descent method

Affiliation(s): College of Computer Science, Sichuan University, Chengdu 610065, China; College of Science, China University of Petroleum, Qingdao 266580, China; less

Received: 2019-10-31 Accepted: 2020-06-12 Available online: 2020-06-12

Next Previous

Abstract

We introduce the fractional-order global optimal backpropagation machine, which is trained by an improved (FSDM). This is a fractional-order backpropagation neural network (FBPNN), a state-of-the-art fractional-order branch of the family of backpropagation neural networks (BPNNs), different from the majority of the previous classic first-order BPNNs which are trained by the traditional first-order steepest descent method. The reverse incremental search of the proposed FBPNN is in the negative directions of the approximate fractional-order partial derivatives of the square error. First, the theoretical concept of an FBPNN trained by an improved FSDM is described mathematically. Then, the mathematical proof of fractional-order global optimal convergence, an assumption of the structure, and of the FBPNN are analyzed in detail. Finally, we perform three (types of) experiments to compare the performances of an FBPNN and a classic first-order BPNN, i.e., example function approximation, , and comparison of global search and error fitting abilities with real data. The higher optimal search ability of an FBPNN to determine the global optimal solution is the major advantage that makes the FBPNN superior to a classic first-order BPNN.

Related Research