On the base of initial weights, through a certain number of user’s feedback training process, weights knowledge base can be stabilized.
在初始权值的基础上,通过一定次数的用户反馈训练过程,权值知识库可以趋于稳定。
参考来源 - 基于模型分割和特征集成的三维模型检索方法研究·2,447,543篇论文数据,部分数据来源于NoteExpress
The self-correlation correction for initial weights of network is studied.
研究了网络初始权值的自相关修正法。
The initial weights and biases of the artificial neural network(ANN)are obtained by offline training method.
人工神经网络(ANN)的初始权值和阈值通过离线训练的方式获得。
The extracted initial rules and their accuracy and coverage are used to configure the fuzzy perceptron structure and initial weights for training.
网络的结构由已经抽取的规则映射而成,初始连接权由规则的精确度和覆盖度确定。
应用推荐