以“tanh”作为激活和“交叉熵”作为成本函数的神经网络不起作用。

I have implemented a simple neural network. It works well with 'sigmoid + cross-entropy', 'sigmoid + quadratic cost', and 'tanh + quadratic cost', but it did not work with 'tanh + cross-entropy' (no better than randomly guess). Can anybody please help me figure out why? Just see the code of FullConnectedLayer:I have implemented a simple neural network. It