排序方式: 共有2条查询结果,搜索用时 15 毫秒
1
1.
2.
LIANG Xun XIA Shaowei Department of Automation Qinghua University Beijing P.R. China 《系统科学与系统工程学报(英文版)》1993,(3)
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 相似文献
1