*{moderator edit - solution code removed}*

In the function initialize_velocity()，we’ve initialized v to v[“dW1”] =[[0. 0. 0.][0. 0. 0.]]…，which means that “v[“dW” + str(l)] = beta * v[“dW” + str(l)] + (1 - beta) * grads[“dW” + str(l)]” is equal to “v[“dW” + str(l)] = (1 - beta) * grads[“dW” + str(l)]” or we’ve just scaled V a little bit use (1 - beta). However, I think the equation should look something like this ”Vdw(l) = beta * Vdw(l-1) + (1 - beta) * dw"