Incremental extreme learning machine
This new theory shows that in order to let SLFNs work as universal approximators, one may simply randomly choose input-to-hidden nodes, and then we only need to adjust the output weights linking the hidden layer and the output layer. In such SLFNs implementations, the activation functions for additi...
Saved in:
主要作者: | |
---|---|
其他作者: | |
格式: | Theses and Dissertations |
出版: |
2008
|
主題: | |
在線閱讀: | https://hdl.handle.net/10356/3804 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
機構: | Nanyang Technological University |
總結: | This new theory shows that in order to let SLFNs work as universal approximators, one may simply randomly choose input-to-hidden nodes, and then we only need to adjust the output weights linking the hidden layer and the output layer. In such SLFNs implementations, the activation functions for additive nodes can be any bounded nonconstant piecewise continuous functions or the activation functions for RBF nodes can be any integrable piecewise continuous functions.We propose two incremental algorithms:1) Incremental extreme learning machine (I-ELM) 2) Convex I-ELM (CI-ELM). |
---|