摘要
神经网络的优化方法一般仅局限于学习算法、输入属性方面。由于神经网络拟合的高维映射存在复杂的内在属性依赖关系,而传统的优化方法却没有对其进行分析研究。以函数依赖理论为基础,提出了属性依赖理论,阐述了属性依赖的有关定义,证明了相关定理;并且与径向基函数(RBF)神经网络结合,提出了基于属性依赖理论的RBF神经网络结构优化方法(ADO-RBF)。最后通过实例证明了该方法在实际应用中的可行性。
Neural network optimization methods are generally confined to learning algorithms and input attributes.Due to the high-dimensional mapping that neural network fits contains complex intrinsic attribute dependencies,the traditional optimization methods have not conducted the analytical study on it.The article put forward the attribute dependency theory based on functional dependency theory,elaborated the definition of the attribute dependency theory,and proved related theorem.Combining the Radius Basis Function（RBF）neural network,a new neural network optimization method based on attribute dependency theory（ADO-RBF）was proposed.
出处
《计算机应用》
CSCD
北大核心
2010年第4期985-989,共5页
journal of Computer Applications
基金
国家自然科学基金资助项目(60272089)
广东省自然科学基金资助项目(980406
04009464)
关键词
函数依赖
属性依赖
属性空间
高维映射
复合型神经网络
functional dependency
attribute dependency
attribute space
high-dimensional mapping
composite neural network
