¹Office of Scientific Research and Practical Training, Cangzhou Technical College, Cangzhou 061001, China.
²Department of Information Engineering, Cangzhou Technical College, Cangzhou 061001, China.
³College of Computer Science & Software Engineering, Shenzhen University, Shenzhen 518060, China.
⁴Department of Computer Science, Bahauddin Zakariya University, Multan, Pakistan.

---

Abstract—Local Coupled Extreme Learning Machine (LCELM) is a recently-proposed variant of ELM, which assigns an address for each hidden-layer node and activates the hidden-layer node when its activated degree is less than a given threshold. In this paper, an improved version of LCELM is proposed by developing a new way to initialize the address for each hidden-layer node and calculating the activated degree of hidden-layer node with Gaussian kernel. The experimental comparison with ELM and LCELM demonstrates the feasibility and effectiveness of improve LCELM which obtains the higher testing accuracy without significantly increasing the training time of ELM.

Index Terms—Extreme learning machine, address of hidden-layer node, window function, Gaussian kernel.

[PDF]

Cite: Chong Liu, Bing Qiang Wang, Xiao Lan Wang, Yu Lin He, Rana Aamir Raza Ashfaq,, "An Improved Local Coupled Extreme Learning Machine," Journal of Software vol. 11, no. 8, pp. 745-755, 2016.