Authors: Kang Li, Jing Deng, Hai-Bo He, Da-Jun Du
Addresses: School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, Belfast, BT9 5AH, UK. ' School of Electronics, Electrical Engineering and Computer Science, Queen's University Belfast, Belfast, BT9 5AH, UK. ' Department of Electrical, Computer and Biomedical Engineering, University of Rhode Island, Kingston, RI 02881, USA. ' School of Mechatronical Engineering and Automation, Shanghai University, Shanghai 200072, China
Abstract: In biological system modelling using data-driven black-box methods, it is essential to effectively and efficiently produce a parsimonious model to represent the system behaviour. The Extreme Learning Machine (ELM) is a recent development in fast learning paradigms. However, the derived model is not necessarily sparse. In this paper, an improved ELM is investigated, aiming to obtain a more compact model without significantly increasing the overall computational complexity. This is achieved by associating each model term to a regularized parameter, thus insignificant ones are automatically unselected, leading to improved model sparsity. Experimental results on biochemical data confirm its effectiveness.
Keywords: ELM; extreme learning machines; fast recursive algorithms; linear-in-the-parameter; local regularisation; radial basis function; MAPK; SOS response; modelling; biochemical data; signal transduction pathway; transcriptional network; DNA damage; E. coli; simulation; computational biology.
International Journal of Computational Biology and Drug Design, 2010 Vol.3 No.2, pp.112 - 132
Received: 26 Oct 2010
Accepted: 29 Oct 2010
Published online: 16 Sep 2010 *