| Global Optimization of Feedforward Neural Networks |
| |
| 引用本文： | LIANG Xun XIA Shaowei Department of Automation,Qinghua University,Beijing 100084,P.R. China. Global Optimization of Feedforward Neural Networks[J]. 系统科学与系统工程学报(英文版), 1993, 0(3) |
| |
| 作者姓名： | LIANG Xun XIA Shaowei Department of Automation Qinghua University Beijing 100084 P.R. China |
| |
| 作者单位： | LIANG Xun XIA Shaowei Department of Automation，Qinghua University，Beijing 100084，P.R. China |
| |
| 基金项目： | This work is supported by Laboratory of Management,Decision and Information Systems,Academia Sinica. |
| |
| 摘 要： | This paper proposes the compensating methods feedforward neural networkd (FNNs)which are very difficult to train by traditional Back Propagation(BP)methods.For an FNN trappedin local minima the compensating methods can correct the wrong outputs one by one until all outputsare right,then the network is located at a global optimum point.A hidden neuron is added to
|
Global Optimization of Feedforward Neural Networks |
| |
| LIANG Xun XIA Shaowei. Global Optimization of Feedforward Neural Networks[J]. Journal of Systems Science and Systems Engineering, 1993, 0(3) |
| |
| Authors: | LIANG Xun XIA Shaowei |
| |
| Affiliation: | LIANG Xun XIA Shaowei Department of Automation,Qinghua University,Beijing 100084,P.R. China |
| |
| Abstract: | This paper proposes the compensating methods for feedforward neural networks (FNNs) which are very difficult to train by traditional Back Propagation (BP) methods. For an FNN trapped in local minima the compensating methods can correct the wrong outputs one by one until all outputs are right, then the network is located at a global optimum point. A hidden neuron is added to compensate for a binary input three-layer FNN trapped in a local minimum, and one or two hidden neurons are added to compensate for a real input three-layer FNN. For a more than three layers FNN, the second hidden layer from behind will be temporarily treated as the input layer during compensation, hence the above methods can also be used. |
| |
| Keywords: | feedforward neurai networks (FNNs) global optimization compensate hidden neuron. |
| 本文献已被 CNKI 等数据库收录！ |
