Abstract
This paper presents a new learning algorithm for multi-layer feed-forward artificial neural networks. The subject transforms into an optimal value of the multivariate function through taking the error square sum of all output unit on all samples as objective function, that is multivariate function of weighting coefficient Using batch method of the output error and step-changing directly adjusting method of the weight, the algorithm has fast learning speed and high precision.
| Original language | English |
|---|---|
| Pages (from-to) | 189-193 |
| Number of pages | 5 |
| Journal | Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology |
| Volume | 17 |
| Issue number | 2 |
| Publication status | Published - 1997 |
Keywords
- Artificial neural networks
- Fault diagnosis
- Monitoring
- Optimum algorithm