Adjust at the end

Hi,

I don't know if it was already said, but it is still not fixed in the code.
When you are training your model, you calculate the weights_deltas between hidden layer and output layer.
But you are updating your weights too early, you are using the new weights to calculate deltas for previous weights (for back-propagation).
You have to keep deltas in memory then update at the end after the rest.

That's why your model takes a lot of time to be trained for the XOR problem. It shouldn't be that long. By memory you have took 50000 iterations. That is too big for a problem like this.

Keep going ^^.

P.S.: Sorry if my english is not perfect, it is not my main natural language.

首先在 repository 中定位 training 和 back-propagation 代码，并复现 issue 中描述的 XOR 案例。检查权重增量在完整的 back-propagation 步骤完成之前始终可用，然后验证 XOR training 无需 50000 次迭代即可收敛。

由索引模型根据 Issue 内容生成。