@inproceedings{e3a47d5090d34d70a268002cd6d31238,
title = "A fast learning algorithm for multi-layer extreme learning machine",
abstract = "Extreme learning machine (ELM) is an efficient training algorithm originally proposed for single-hidden layer feedforward networks (SLFNs), of which the input weights are randomly chosen and need not to be fine-tuned. In this paper, we present a new stack architecture for ELM, to further improve the learning accuracy of ELM while maintaining its advantage of training speed. By exploiting the hidden information of ELM random feature space, a recovery-based training model is developed and incorporated into the proposed ELM stack architecture. Experimental results of the MNIST handwriting dataset demonstrate that the proposed algorithm achieves better and much faster convergence than the state-of-the-art ELM and deep learning methods.",
keywords = "Extreme learning machine (ELM), deep learning, multi-layer training, sparse representation",
author = "Jiexiong Tang and Chenwei Deng and Huang, \{Guang Bin\} and Junhui Hou",
note = "Publisher Copyright: {\textcopyright} 2014 IEEE.",
year = "2014",
month = jan,
day = "28",
doi = "10.1109/ICIP.2014.7025034",
language = "English",
series = "2014 IEEE International Conference on Image Processing, ICIP 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "175--178",
booktitle = "2014 IEEE International Conference on Image Processing, ICIP 2014",
address = "United States",
}