Entropy-Constraiend Generalized Learning Vector Quantization Neural Network and Soft Competitive Learning Algorithm
-
摘要: 结合广义学习矢量量化神经网络的思想和信息论中的极大熵原理,提出了一种熵约束 广义学习矢量量化神经网络,利用梯度下降法导出其学习算法,该算法是软竞争格式的一种推 广.由于亏损因子和尺度函数被定义为同一个模糊隶属度函数,它可以有效地克服广义学习矢 量量化网络的模糊算法存在的问题.文中还给出熵约束广义学习矢量量化网络及其软竞争学习 算法的许多重要性质,以此为依据,讨论拉格朗日乘子的选取规则.Abstract: According to the generalized learning vector quantization (GLVQ) network and the maximum-entropy principle, an entropy-constrained generalized learning vector quantization (ECGLVQ) neural network is proposed in this paper. A learning algorithm of the network, a generalization of the soft-competition scheme (SCS), is derived via the gradient descent method. Because the loss factor and the corresponding scaling function are defined as the same fuzzy membership function, it can overcome the problems for fuzzy algorithms of GLVQ network possess. Many important properties of the ECGLVQ network and its soft competitive learning algorithm are given. Thereby, the rule for choosing the Lagrangian multiplier is designed.
-
点击查看大图
计量
- 文章访问数: 2707
- HTML全文浏览量: 139
- PDF下载量: 995
- 被引次数: 0
下载:
