针对文本中事件专题挖掘,提出事件模型学习算法。
For text-mining method of event topic, the method of event model was also proposed.
本文从神经网络模型的结构出发,对学习算法提出了一系列改进和优化措施,以加快网络的学习速度,并增加模型的稳定性。
With the study of neural network model, this paper advances some of improvement and optimization techniques that can accelerate the learning speed of network and increase the stability of model.
提出基于TDNN神经网络的线性噪声消除器,讨论了它的模型与学习算法及其通用逼近性。
Linear noise canceller based on TDNN was proposed, and its model, learning algorithm and universal approximation were discussed.
应用推荐