Extreme Learning Machine based on Rectified Nonlinear Units
Authors
Jingtao Peng, Liang Chen, Iqbal Muhammad Ather, Ao Yu
Corresponding Author
Jingtao Peng
Available Online May 2016.
- DOI
- 10.2991/wartia-16.2016.309How to use a DOI?
- Keywords
- Extreme Learning machine, Over-saturation, Rectified Linear Units, Rectified Non-Linear Units
- Abstract
Traditional Extreme Learning Machine (ELM) networks generally used S-shaped activation function, such as Sigmoid function and Tangent function. However, the problems of slow convergence speed and over-saturation exist. In order to solve the above problems and improve the performance of ELM algorithm, the method of Rectified Non-Linear Units (ReNLUs), combining rectified linear units (ReLUs) with Softplus function method, was proposed. And the ReLUs has the ability of sparse expression and the Softplus possesses smooth and unsaturated features. Experimental results show that the ELM with the method of ReNLUs activation function, the accuracy and time of training and testing have been significantly improved and saved.
- Copyright
- © 2016, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Jingtao Peng AU - Liang Chen AU - Iqbal Muhammad Ather AU - Ao Yu PY - 2016/05 DA - 2016/05 TI - Extreme Learning Machine based on Rectified Nonlinear Units BT - Proceedings of the 2016 2nd Workshop on Advanced Research and Technology in Industry Applications PB - Atlantis Press SP - 1523 EP - 1528 SN - 2352-5401 UR - https://doi.org/10.2991/wartia-16.2016.309 DO - 10.2991/wartia-16.2016.309 ID - Peng2016/05 ER -