期刊论文

Li, Long

英文

Neurocomputing

0925-2312

2017

260

404-410

10.1016/j.neucom.2017.04.046

This work is partially supported by the Natural Science Foundation of China (11401185, 61403056), Scientific Research Fund of Hunan Provincial Education Department (13B004), Hunan Provincial Natural Science Foundation of China (14JJ6039) and the Science and Technology Plan Project of Hunan Province (2016TP1020). The author (Qiao) also thanks the UTRGV President't Endowed Professorship and the UTRGV College of Science seed grant for their partial supports. This work is partially supported by the Natural Science Foundation of China ( 11401185 , 61403056 ), Scientific Research Fund of Hunan Provincial Education Department (13B004), Hunan Provincial Natural Science Foundation of China ( 14JJ6039 ) and the Science and Technology Plan Project of Hunan Province (2016TP1020). The author (Qiao) also thanks the UTRGV President’t Endowed Professorship and the UTRGV College of Science seed grant for their partial supports.

本校为第一且通讯机构

In this paper, a smooth function is constructed to approximate the nonsmooth output of max –min fuzzy neural networks (FNNs) and its approximation is also presented. In place of the output of max –min FNNs by its smoothing approximation function, the error function, defining the discrepancy between the actual outputs and desired outputs of max –min FNNs, becomes a continuously differentiable function. Then, a smoothing gradient decent-based algorithm with Armijo–Goldstein step size rule is formulated to train max –min FNNs. Based on the ex...