网络结构增长极端学习机算法_李凡军.pdfVIP

31 5 Vol. 31 No. 5 2014 5 Control Theory Applications May 2014 DOI: 10.7641/CTA.2014.31001 , , (1. , 100124; 2. , 250022) : (extreme learning machine, ELM), . Sigmoid: . , ELM, , 1 . 21, . . . : ; ; ; : TP273 : A Incremental constructive extreme learning machine LI Fan-jun , QIAO Jun-fei, HAN Hong-gui (1. College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China; 2. School of Mathematical Science, University of Jinan, Jinan Shandong 250022, China) Abstract: Focusing on the problem of architectural design of extreme learning machine (ELM), we propose a novel constructive algorithm by the activation function and its derivatives. Firstly, taking the Sigmoid function as an example, we give in detail the derived characteristics for a class of base functions: derivative functions can be expressed by their primitive functions. By making use of these derived characteristics, we propose a method to design the structure of ELM, which automatically generate feedforward neural networks with double hidden layers. The new units in the first hidden layer are generated randomly one by one; then, the outputs of the second hidden layer (derivation) are calculated by the activation function of the new node in the first layer and its derivatives. The weights of the output layer are calculated analytically by the least squares method. Finally, the analysis of convergence and stability are presented. The effectiveness of the proposed method is demonstrated by simul