文献类型：期刊文献

英文题名：A novel learning algorithm of single-hidden-layer feedforward neural networks

作者：Pu, Dong-Mei[1];Gao, Da-Qi[1];Ruan, Tong[1];Yuan, Yu-Bo[1,2]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China;[2]Zhejiang Ocean Univ, Key Lab Oceanog Big Data Min & Applicat Zhejiang, Zhoushan 316022, Zhejiang, Peoples R China

年份：2017

卷号：28

起止页码：S719

外文期刊名：NEURAL COMPUTING & APPLICATIONS

收录：;EI(收录号：20162702549934);WOS:【SCI-EXPANDED(收录号:WOS:000417319700059)】；

基金：Authors would like to thank the reviewers for spending a lot of time reading our manuscript, and their comments are very helpful to improve the quality of this paper. This research has been supported by the National High Technology Research and Development Program of China (863 Program) under Grant No. 2015AA020107 and the National Natural Science Foundation under Grant Nos. 61272198, 60675027 and 61001200. This research has been also supported by Key Laboratory of Oceanographic Big Data Mining and Application of Zhejiang Province (No. OBDMA201507).

语种：英文

外文关键词：Neural networks; Iteration methods; Data classification; Data regression; Optimization; Algorithms

摘要：Single-hidden-layer feedforward neural network (SLFN) is an effective model for data classification and regression. However, it has a very important defect that it is rather time-consuming to explore the training algorithm of SLFN. In order to shorten the learning time, a special non-iterative learning algorithm was proposed, named as extreme learning machine (ELM). The main idea is that the input weights and bias are chosen randomly and the output weights are calculated by a pseudo-inverse matrix. However, ELM also has a very important drawback that it cannot achieve stable solution for different runs because of randomness. In this paper, we propose a stabilized learning algorithm based on iteration correction. The convergence analysis shows that the proposed algorithm can finish the learning process in fewer steps than the number of neurons. Three theorems and their proofs can prove that the proposed algorithm is stable. Several data sets are selected from UCI databases, and the experimental results demonstrate that the proposed algorithm is effective.