Compact extreme learning machines for biological systems

Authors

Kang Li, Queen's University Belfast
Jing Deng, Queen's University Belfast
Haibo He, University of Rhode IslandFollow
Da Jun Du, Shanghai University

Document Type

Article

Date of Original Version

1-1-2010

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. © 2010 Inderscience Enterprises Ltd.

Publication Title, e.g., Journal

International Journal of Computational Biology and Drug Design

Volume

3

Issue

2

Citation/Publisher Attribution

Li, Kang, Jing Deng, Haibo He, and Da Jun Du. "Compact extreme learning machines for biological systems." International Journal of Computational Biology and Drug Design 3, 2 (2010): 112-132. doi: 10.1504/IJCBDD.2010.035238.