《2016 Optimization method based extreme learning machine for classication》.pdf

Neurocomputing 74 (2010) 155–163 Contents lists available at ScienceDirect Neurocomputing journal homepage: /locate/neucom Optimization method based extreme learning machine for classification $ Guang-Bin Huang a,, Xiaojian Ding a,b, Hongming Zhou a a School of Electrical and Electronic Engineering, Nanyang Technological University, Nanyang Avenue, Singapore 639798, Singapore b School of Electronic and Information Engineering, Xi’an Jiaotong University, Shaanxi, Xi’an 710049, China a r t i c l e i n f o a b s t r a c t Article history: Extreme learning machine (ELM) as an emergent technology has shown its good performance in Received 8 January 2010 regression applications as well as in large dataset (and/or multi-label) classification applications. The Received in revised form ELM theory shows that the hidden nodes of the ‘‘generalized’’ single-hidden layer feedforward 7 February 2010 networks (SLFNs), which need not be neuron alike, can be randomly generated and the universal Accepted 7 February 2010 approximation capability of such SLFNs can be guaranteed. This paper further studies ELM for Communicated by D. Wang Available online 10 May 2010 classification in the aspect of the standard optimization method and extends ELM to a specific type of ‘‘generalized’’ SLFNs—support vector network. This paper shows that: