高级检索
    李爱军, 罗四维, 黄 华, 刘蕴辉. 基于决策树的神经网络[J]. 计算机研究与发展, 2005, 42(8): 1312-1317.
    引用本文: 李爱军, 罗四维, 黄 华, 刘蕴辉. 基于决策树的神经网络[J]. 计算机研究与发展, 2005, 42(8): 1312-1317.
    Li Aijun, Luo Siwei, Huang Hua, Liu Yunhui. Decision Tree Based Neural Network Design[J]. Journal of Computer Research and Development, 2005, 42(8): 1312-1317.
    Citation: Li Aijun, Luo Siwei, Huang Hua, Liu Yunhui. Decision Tree Based Neural Network Design[J]. Journal of Computer Research and Development, 2005, 42(8): 1312-1317.

    基于决策树的神经网络

    Decision Tree Based Neural Network Design

    • 摘要: 传统人工神经网络模型采用试探的方法确定合适的网络结构,并随机地初始化参数值,导致神经网络训练效率低、结果不稳定.熵网络是一种建立在决策树之上的3层前馈网络,在熵网络基础上,提出了基于决策树的神经网络设计方法(DTBNN). DTBNN中提供了对神经网络参数的初始值合理设置的方法,并提出了由决策树确定的只是熵网络的初始结构,在实际的网络构造中需要根据实际应用添加神经元和连接权以提高网络的性能.理论分析和实验结果表明了这种方法的合理性.

       

      Abstract: The structure determination and parameter initialization of an artificial neural network (ANN) is of great importance to its performance. Generally a network is built by trial and error methods with its parameters randomly initialized. Such practice results in low training efficiency and instability of a network. Based on the functional similarity and equivalence of decision tree and ANN, a new network construction and initialization method is proposed, which is called decision tree based neural network (DTBNN for short). The method is mainly based on the entropy net, but has several improvements. Firstly, an initial network structure is determined according to the information of a decision tree. The structure is then optimized by adding neurons and connections in accordance with practical requirements. Secondly, the network is then initialized so that the hyper-plane it represents is much closer to its final version. By these means, the limitations of entropy net are avoided. Network built by this method has shown good performance. Theoretical analysis and experimental results have shown its effectiveness.

       

    /

    返回文章
    返回