Hello,
I am a little confused with the optional assignment for the function `run_backward`. The gradients for the single time step is correctly calculated. However, this particular function shows me wrong values. The shape of the output arrays are correct, though. I have already consulted the other questions in this forum for possible hints, but I am still not able to figure out where I am wrong. It would be helpful if someone supplies me with some more suggestions. Thanks in advance.