loop pseudocode for backprop article

loop.py

    def train_network(network, iterations, alpha):
        for i in range(iterations):
            # forward
            for layer in network[1:]:
                layer.nodes = activation_function((layer-1).nodes @ layer.weights)
            # backward
            for layer in network.reverse(): # We iterate our network in reverse order.
                if layer is output_layer: # Calculate the loss
                    ∂_L =  network[L].nodes - labels
                elif layer is (output_layer-1): # These are the first weights to be updated (W100 in the diagrams)
                    ∆w.append(alpha * layer-1.nodes.T @ (∂_L * activation_derivative((layer).nodes)))
                else:
                    ∂_L = ∂_L  @ (layer+1).weights.T * activation_derivative((layer+1).nodes)
                    ∆w.append(alpha * (layer-1).nodes.T @ (∂_L * activation_derivative(layer.nodes)))

        # update weights:
            network.weights += ∆w