0

I want to define a function approximation by RBF neural network in MATLAB.

RBF needs there parameters as "unit centers", "sigma" and "weight". I have a dataset by 1000 records and 10 features.

first question: these three parameters should be in an array format? or can be in matrix format?

second question: I defined "unit centers" by k-means clustering over dataset. This is three cluster centers. For "sigma" and "weight" parameters, i should define a matrix same as the "unit centers" size?

unit centers are matrix by 3*10 size. Other two RBF parameters should assign in 3in10 size? Or can i define them in 1in10 or 2in10 size?

4

1 回答 1

0

中心当然是矩阵的形式,你有 10 个特征,你正在根据这 10 个维度按距离计算中心。并且您有多个中心,因此它是一个形状矩阵:(#centers,#features)。

Sigma 只是每个中心的一个数字,因此它的形状为:(#centers,1),因此它是一维数组

权重取决于隐藏层(中心)的大小,一个输出神经元的形状为:(#centers,1),它是一个一维数组

这里要提到的最后一件事是,与输入大小(1000)相比,您的中心数量很小。如果您在测试集上没有获得良好的准确性,请尝试 100、200 甚至 500 个中心。

于 2018-10-25T14:34:38.413 回答