Timeline for Why not Back propagate through time in LSTM , similar to RNN
Current License: CC BY-SA 4.0
2 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 31 at 14:41 | comment | added | Amith Adiraju | Thanks for taking time ! Your explanation on Truncated backprop makes sense.My questions are two fold: 1) If one does grad check with truncated backprop, there is no way grad check is going to pass right ? 2) What is the theoretical derivation of LSTM's backprop , is that similar to RNN's BPTT , or different ? to check if my implementation of LSTM is right, I need to know "2" and then do grad check. I can only move to "1" after I pass grad check. If I can't do grad check, I wouldn't know if my implementation is right. | |
| Jan 31 at 4:48 | history | answered | Karl | CC BY-SA 4.0 |