I am reading through [this article][1] trying to understand the bptt algorithm, in the context of an RNN. There is one part I don’t understand: 

    layer_1_delta = (future_layer_1_delta.dot(synapse_h.T) + 
        layer_2_delta.dot(synapse_1.T)) +     
        sigmoid_output_to_derivative(layer_1)
    
    # Located on line 99 in the article linked above 

I can’t seem to figure out which mathematical formula this links to in the bptt algorithm to understand what it does, so could someone please provide it? Many thanks 


  [1]: https://iamtrask.github.io/2015/11/15/anyone-can-code-lstm/