In this paper we explore and discuss the learning and generalization characteristics of the random vector version of the Functional-link net and compare these with those attainable with the GDR algorithm. This is done for a well-behaved deterministic function and for real-world data. It seems that 'overtraining' occurs for stochastic mappings. Otherwise there is saturation of training.
机构:
State Key Laboratory of Synthetical Automation for Process Industries,Northeastern UniversityState Key Laboratory of Synthetical Automation for Process Industries,Northeastern University
Li ZHANG
Ping ZHOU
论文数: 0引用数: 0
h-index: 0
机构:
State Key Laboratory of Synthetical Automation for Process Industries,Northeastern UniversityState Key Laboratory of Synthetical Automation for Process Industries,Northeastern University
Ping ZHOU
He-da SONG
论文数: 0引用数: 0
h-index: 0
机构:
State Key Laboratory of Synthetical Automation for Process Industries,Northeastern UniversityState Key Laboratory of Synthetical Automation for Process Industries,Northeastern University
He-da SONG
Meng YUAN
论文数: 0引用数: 0
h-index: 0
机构:
Department of Mechanical Engineering,University of MelbourneState Key Laboratory of Synthetical Automation for Process Industries,Northeastern University
Meng YUAN
Tian-you CHAI
论文数: 0引用数: 0
h-index: 0
机构:
State Key Laboratory of Synthetical Automation for Process Industries,Northeastern UniversityState Key Laboratory of Synthetical Automation for Process Industries,Northeastern University