神经网络的过度拟合问题

Question

神经网络的过度拟合是因为隐层个数大于样本的变量个数，还是因为神经元的个数大于样本个数？
when the neural element number n of neural networks is larger than the sample size m, the overfitting problem arises since there are more parameters than actual data.(more variable than constraints)
就是这句我不确定。