摘要
Compared with deep neural learning, the extreme learning machine (ELM) can be quickly converged without iteratively tuning hidden nodes. Inspired by this merit, an extreme learning machine with elastic net regularization (ELM-EN) is proposed in this paper. The elastic net is a regularization method that combines LASSO and ridge penalties. This regulartation can keep a balance between system stability and solution's sparsity. Moreover, an excellent optimization method, i.e., accelerated proximal gradient, is used to find the minimum of the system optimization function. Various datasets from UCI repository and two facial expression image datasets are used to validate the efficiency of our system. Final experimental results indicate that our ELM-EN requires less training tine than multi-layer perceptron, and can achieve higher recognition accuracy than ELM and sparse ELM.
学科与关键词
- ELM Regularized Method for Classification ProblemsCarrasco, Juan J.*; Millan-Giraldo, Monica; Caravaca, Juan*; Escandoll-Montero, Pablo*; Martinez-Martinez, Jose M.*; Soria-Olivas, Emilio*International Journal on Artificial Intelligence Tools, 2016, 25(1): 1550026.被引 9
- Smoothing L0 Regularization for Extreme Learning MachineFan, Qinwei*; Liu, TingMATHEMATICAL PROBLEMS IN ENGINEERING, 2020, 2020: 9175106.被引 5
- A review on extreme learning machineWang, Jian; Lu, Siyuan; Wang, Shui-Hua*; Zhang, Yu-Dong*MULTIMEDIA TOOLS AND APPLICATIONS, 2022, 81(29): 41611-41660.被引 226
