Timeline for Efficient recurrent network for sequences of varying length
Current License: CC BY-SA 4.0
4 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 18, 2019 at 1:39 | vote | accept | steam_engine | ||
| Dec 17, 2019 at 16:01 | comment | added | Noah Weber | There are different techniques to solve this, at the end of the day, optimisation problem. What you said is one way, that could be expensive (depending on the data) You can also use arbitrary batches and depending on the size of the longest in every batch padd accordingly. Have a look at here medium.com/@rashmi.margani/… | |
| Dec 17, 2019 at 15:54 | comment | added | steam_engine | I had a glance. It seems like breaking data into smaller batches, long going with long and short going with short, correct? | |
| Dec 17, 2019 at 14:27 | history | answered | Noah Weber | CC BY-SA 4.0 |