The optimization design method is proposed for feed-forward neural network structure by means of chaos ergodicity and randomicity.
提出一种关于多层前向神经网络结构的混沌优化设计方法。
Optimization of corona ring design for EHV composite insulator using finite element and neural network method.
基于有限元和神经网络方法对超高压合成绝缘子均压环结构优化的研究。
Combining grading method with chaotic optimization, the neural network model achieves rapid training and avoids local minimum when there are a lot of samples to be trained.
考虑神经网络在训练大规模样品时易陷入局部极小，用梯度下降法与混沌优化方法相结合，使神经网络实现快速训练的同时，避免陷入局部极小。
应用推荐