Skip to main content
4 events
when toggle format what by license comment
Apr 5, 2020 at 19:25 comment added Jeremiah England @nbro If you're talking about the original 1997 paper by Hochreiter and Schmidhuber, there is no mention of 'clip'/'clipping' and all the instances of 'truncate' appear to be in reference to truncating the BPTT algorithm, not the gradients themselves.
Apr 5, 2020 at 17:40 comment added nbro Maybe have also a look at the LSTM paper. It probably talks about the topic too.
Apr 5, 2020 at 17:32 vote accept Jeremiah England
Apr 5, 2020 at 17:30 history answered Jeremiah England CC BY-SA 4.0