\input zb-basic
\input zb-ioport
\iteman{io-port 06059008}
\itemau{Han, Fei; Yao, Hai-Fen; Ling, Qing-Hua}
\itemti{An improved extreme learning machine based on particle swarm optimization.}
\itemso{Huang, De-Shuang (ed.) et al., Bio-inspired computing and applications. 7th international conference on intelligent computing, ICIC 2011, Zhengzhou, China, August 11--14. 2011. Revised selected papers. Berlin: Springer (ISBN 978-3-642-24552-7/pbk). Lecture Notes in Computer Science 6840. Lecture Notes in Bioinformatics, 699-704 (2012).}
\itemab
Summary: Traditional extreme learning machine (ELM) may require high number of hidden neurons and lead to ill-condition problem due to the random determination of the input weights and hidden biases. In this paper, we use a modified particle swarm optimization (PSO) algorithm to select the input weights and hidden biases of single-hidden-layer feedforward neural networks (SLFN) and Moore-Penrose (MP) generalized inverse to analytically determine the output weights. The modified PSO optimizes the input weights and hidden biases according to not only the root mean squared error on validation set but also the norm of the output weights. The proposed algorithm has better generalization performance than other ELMs and its conditioning is also improved.
\itemrv{~}
\itemcc{}
\itemut{extreme learning machine; particle swarm optimization; generalization performance}
\itemli{doi:10.1007/978-3-642-24553-4\_92}
\end