RNN formula is incorrect

[travis-leith]

The current formula is something like
$h(t)=W_{ih}X(t)+b_{ih}+W_{hh}X(t-1)+b_{hh}$
but it should be something like
$h(t)=W_{ih}X(t)+b_{ih}+W_{hh}h(t-1)+b_{hh}$

The difference is that it is the previous state, not the previous inputs that are fed back into the network.

See official torch docs for confirmation: https://docs.pytorch.org/docs/stable/generated/torch.nn.RNN.html