TY - GEN
T1 - A brain network inspired algorithm
T2 - 24th International Conference on Neural Information Processing, ICONIP 2017
AU - Zhang, Yongshan
AU - Wu, Jia
AU - Cai, Zhihua
AU - Jiang, Siwei
N1 - An erratum exists for this publication and the original paper has been corrected. The erratum can be found at doi: 10.1007/978-3-319-70139-4_94
PY - 2017
Y1 - 2017
N2 - Extreme learning machine (ELM) is a promising learning method for training “generalized” single hidden layer feedforward neural networks (SLFNs), which has attracted significant interest recently for its fast learning speed, good generalization ability and ease of implementation. However, due to its manually selected network parameters (e.g., the input weights and hidden biases), the performance of ELM may be easily deteriorated. In this paper, we propose a novel pre-trained extreme learning machine (P-ELM for short) for classification problems. In P-ELM, the superior network parameters are pre-trained by an ELM-based autoencoder (ELM-AE) and embedded with the underlying data information, which can improve the performance of the proposed method. Experiments and comparisons on face image recognition and handwritten image annotation applications demonstrate that P-ELM is promising and achieves superior results compared to the original ELM algorithm and other ELM-based algorithms.
AB - Extreme learning machine (ELM) is a promising learning method for training “generalized” single hidden layer feedforward neural networks (SLFNs), which has attracted significant interest recently for its fast learning speed, good generalization ability and ease of implementation. However, due to its manually selected network parameters (e.g., the input weights and hidden biases), the performance of ELM may be easily deteriorated. In this paper, we propose a novel pre-trained extreme learning machine (P-ELM for short) for classification problems. In P-ELM, the superior network parameters are pre-trained by an ELM-based autoencoder (ELM-AE) and embedded with the underlying data information, which can improve the performance of the proposed method. Experiments and comparisons on face image recognition and handwritten image annotation applications demonstrate that P-ELM is promising and achieves superior results compared to the original ELM algorithm and other ELM-based algorithms.
KW - Classification
KW - ELM-based autoencoder
KW - Extreme learning machine
KW - Pre-trained parameter
UR - http://www.scopus.com/inward/record.url?scp=85035137982&partnerID=8YFLogxK
UR - https://doi.org/10.1007/978-3-319-70139-4_94
U2 - 10.1007/978-3-319-70139-4_2
DO - 10.1007/978-3-319-70139-4_2
M3 - Conference proceeding contribution
AN - SCOPUS:85035137982
SN - 9783319701387
T3 - Lecture Notes in Computer Science
SP - 14
EP - 23
BT - Neural information processing
A2 - Liu, Derong
A2 - Xie, Shengli
A2 - Li, Yuanqing
A2 - Zhao, Dongbin
A2 - El-Alfy, El-Sayed M.
PB - Springer, Springer Nature
CY - Cham, Switzerland
Y2 - 14 November 2017 through 18 November 2017
ER -