Robust single hidden layer feed-forward neural networks modeling for small datasets

Rong Zhang, Zhao Hong Deng, Shi Tong Wang, Kup Sze Choi, Peng Jiang Qian

Research output: Journal article publicationJournal articleAcademic researchpeer-review

Abstract

Single hidden layer feed-forward neural network (SLFN) is one of the most widely used models for intelligent modeling. But the model faces that for small sample sets, the traditional learning algorithm may train a model to fall into the over-fitting sate. In particular, when the dataset contains a large amount of noise, the trained model has weak robustness and is very sensitive to noise. In order to overcome this shortcoming, a robust learning algorithm of SLFN is derived for small and noisy datasets. Due to the introduction of ε-insensitive learning measure and the structural risk term, the proposed algorithm can effectively overcome the shortcoming of the traditional learning algorithm. The experimental results on simulated and real-world datasets also confirm the above advantages.
Original languageChinese (Simplified)
JournalKongzhi yu Juece/Control and Decision
Volume27
Issue number9
Publication statusPublished - 1 Sep 2012

Keywords

  • ε-insensitive learning
  • Robustness
  • Single hidden layer feed-forward neural network
  • Structural risk minimization

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Control and Optimization
  • Artificial Intelligence

Cite this