Yang Zhiyong, Zhang Taohong, Zhang Dezheng
Department of Computer, School of Computer and Communication Engineering, University of Science and Technology Beijing (USTB), Beijing, 100083 China ; Beijing Key Laboratory of Knowledge Engineering for Materials Science, Beijing, 100083 China.
Cogn Neurodyn. 2016 Feb;10(1):73-83. doi: 10.1007/s11571-015-9358-9. Epub 2015 Oct 17.
Extreme learning machine (ELM) is a novel and fast learning method to train single layer feed-forward networks. However due to the demand for larger number of hidden neurons, the prediction speed of ELM is not fast enough. An evolutionary based ELM with differential evolution (DE) has been proposed to reduce the prediction time of original ELM. But it may still get stuck at local optima. In this paper, a novel algorithm hybridizing DE and metaheuristic coral reef optimization (CRO), which is called differential evolution coral reef optimization (DECRO), is proposed to balance the explorative power and exploitive power to reach better performance. The thought and the implement of DECRO algorithm are discussed in this article with detail. DE, CRO and DECRO are applied to ELM training respectively. Experimental results show that DECRO-ELM can reduce the prediction time of original ELM, and obtain better performance for training ELM than both DE and CRO.
极限学习机（ELM）是一种用于训练单层前馈网络的新颖且快速的学习方法。然而，由于需要大量的隐藏神经元，ELM的预测速度不够快。为了减少原始ELM的预测时间，提出了一种基于差分进化（DE）的进化ELM。但它仍可能陷入局部最优。本文提出了一种将DE与元启发式珊瑚礁优化（CRO）相结合的新算法，称为差分进化珊瑚礁优化（DECRO），以平衡探索能力和开发能力，从而获得更好的性能。本文详细讨论了DECRO算法的思想和实现。DE、CRO和DECRO分别应用于ELM训练。实验结果表明，DECRO-ELM可以减少原始ELM的预测时间，并且在训练ELM方面比DE和CRO都具有更好的性能。
