问题描述
我经常出错在C#中使用方法 SetRBFCentersAndWidthsEqualSpacing ，RBF神经元的总数必须是'dimensions'幂的整数.
I get constantly error Total number of RBF neurons must be some integer to the power of 'dimensions' with using method SetRBFCentersAndWidthsEqualSpacing in C#.
在Encog中熟悉RBF网络的人可以检查RBFNetwork.cs中的232行.我认为可能是一个错误或我错过了一些东西:
Can someone who is familiar with RBF network in Encog check the line 232 in RBFNetwork.cs. I think there is maybe a bug or I miss something:
var expectedSideLength = (int) Math.Pow(totalNumHiddenNeurons, 1.0d/dimensions);
double cmp = Math.Pow(totalNumHiddenNeurons, 1.0d/dimensions);
if (expectedSideLength != cmp) -> error
这两个变量不能相等，因为(int)将数字四舍五入.巧合的是，它适用于XOR示例，不适用于19等不同维度.
these two variables can't be equal, because (int) rounds the number. It's coincidence that it works for XOR example, it won't work with different dimenson like 19 for example.
这是我创建RBF网络的方法:
This is how I create RBF network:
dataSet is VersatileMLDataSet
RBFNetwork n = new RBFNetwork(dataSet.CalculatedInputSize, dataSet.Count, 1, RBFEnum.Gaussian);
n.SetRBFCentersAndWidthsEqualSpacing(0, 1, RBFEnum.Gaussian, 2.0/(dataSet.CalculatedInputSize * dataSet.CalculatedInputSize), true);
我的数据集有19个属性(维度)和731条记录.
My dataset has 19 attributes (dimension) with 731 records.
推荐答案
隐藏神经元的数量是一个整数，它提高了输入神经元数量的幂.因此，如果您有3个输入属性且窗口大小为2，则隐藏的神经元将是任何整数(例如3)，其乘幂为6(3 x 2)或729.这限制了输入属性和窗口大小的数量，因为隐藏神经元的数量很快变得非常大.
The number of hidden neurons is an integer raised to the power of the number of input neurons. So if you have 3 input attributes and a window size of 2, hidden neurons would be any integer (say 3) raised to the power of 6 (3 x 2) or 729. This limits the number of input attributes and window size as the number of hidden neurons gets very large very quickly.
这篇关于Encog RBF C#，RBF神经元总数必须是“维数"的幂的整数的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！