1. Deep Network Based on Stacked Orthogonal Convex Incremental ELM Autoencoders
- Author
-
Chao Wang, Jianhui Wang, and Shusheng Gu
- Subjects
0209 industrial biotechnology ,Optimization problem ,Article Subject ,Computer science ,business.industry ,Generalization ,General Mathematics ,Node (networking) ,lcsh:Mathematics ,General Engineering ,Regular polygon ,02 engineering and technology ,lcsh:QA1-939 ,020901 industrial engineering & automation ,lcsh:TA1-2040 ,Convex optimization ,Incremental learning ,0202 electrical engineering, electronic engineering, information engineering ,020201 artificial intelligence & image processing ,Artificial intelligence ,business ,lcsh:Engineering (General). Civil engineering (General) ,Orthogonalization ,Extreme learning machine - Abstract
Extreme learning machine (ELM) as an emerging technology has recently attracted many researchers’ interest due to its fast learning speed and state-of-the-art generalization ability in the implementation. Meanwhile, the incremental extreme learning machine (I-ELM) based on incremental learning algorithm was proposed which outperforms many popular learning algorithms. However, the incremental algorithms with ELM do not recalculate the output weights of all the existing nodes when a new node is added and cannot obtain the least-squares solution of output weight vectors. In this paper, we propose orthogonal convex incremental learning machine (OCI-ELM) with Gram-Schmidt orthogonalization method and Barron’s convex optimization learning method to solve the nonconvex optimization problem and least-squares solution problem, and then we give the rigorous proofs in theory. Moreover, in this paper, we propose a deep architecture based on stacked OCI-ELM autoencoders according to stacked generalization philosophy for solving large and complex data problems. The experimental results verified with both UCI datasets and large datasets demonstrate that the deep network based on stacked OCI-ELM autoencoders (DOC-IELM-AEs) outperforms the other methods mentioned in the paper with better performance on regression and classification problems.
- Published
- 2016
- Full Text
- View/download PDF