This helper function computes the squared error cost and its derivative

compte_cost.py

def compute_cost(Y, Y_hat):
    """
    This function computes and returns the Cost and its derivative.
    The is function uses the Squared Error Cost function -> (1/2m)*sum(Y - Y_hat)^.2

    Args:
        Y: labels of data
        Y_hat: Predictions(activations) from a last layer, the output layer

    Returns:
        cost: The Squared Error Cost result
        dY_hat: gradient of Cost w.r.t the Y_hat

    """
    m = Y.shape[1]

    cost = (1 / (2 * m)) * np.sum(np.square(Y - Y_hat))
    cost = np.squeeze(cost)  # remove extraneous dimensions to give just a scalar

    dY_hat = -1 / m * (Y - Y_hat)  # derivative of the squared error cost function

    return cost, dY_hat