Wrong formula in back-propagating

[A-Soltani]

I inspected whole of the code, but I guess there is a mistake in this line.
As far as I am concerned, the cost function used in your code is:

Therefore, If you are going to follow delta rule, the data needed for back-propagation is:

But in your code it is:

The difference between them is sigmoid function.
I think there is a small mistake in this line.

recurrent_neural_net_demo/rnn.py

Line 77 in 35fb080

layer_2_deltas.append((layer_2_error)*sigmoid_output_to_derivative(layer_2))