论文信息 - Orthogonal Basis Extreme Learning Algorithm and Function Approximation

Orthogonal Basis Extreme Learning Algorithm and Function Approximation

A new algorithm for single hidden layer feedforward neural networks SLFN, Orthogonal Basis Extreme Learning OBEL algorithm, is proposed and the algorithm derivation is given in the paper. The algorithm can decide both the NNs parameters and the neuron number of hidden layers during training while providing extreme fast learning speed. It will provide a practical way to develop NNs. The simulation results of function approximation showed that the algorithm is effective and feasible with good accuracy and adaptability.

Ying Li | Yan Li | Xiangkui Wan

[1] Chee Kheong Siew,et al. Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[2] Yunong Zhang,et al. Gegenbauer orthogonal basis neural network and its weights-directdetermination method , 2009 .

[3] Lingzhi Wang,et al. Hybrid Neural Network Models for Hydrologic Time Series Forecasting Based on Genetic Algorithm , 2011, 2011 Fourth International Joint Conference on Computational Sciences and Optimization.

[4] Guang-Bin Huang,et al. Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[5] Ying Li,et al. Study on Orthogonal Basis NN-Based Storage Modelling for Lake Hume of Upper Murray River, Australia , 2014, ICMLC.