通过不断试验比较，以优化网络结构为目标，最终选定13-9-5 - 6的双隐含层结构。
By continually practiced and compared, "13-9-5-6" double hidden layers with optimized training structure are confirmed.
为了解决通信网络结构识别问题，根据通信网的工作特点，在识别过程中引入目标编群理论，逐层递增生成通信网络的群结构，并对群结构进行动态维护，识别和更新通信网的组成信息。
In order to solve the problem of recognition of communication networks, the group formation theory is introduced into the procession of recognition according to the characteristics of network.
最后，对BP神经网络的训练目标、网络结构和传递函数等参数进行了优化，初步实现对镰刀菌的分类。
In the end, we initially achieved the classification for Fusarium by optimizing BP neural network training targets, network structure and transfer function.
应用推荐