Timeline for When to use GRU over LSTM?
Current License: CC BY-SA 4.0
7 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| S Aug 26, 2022 at 22:08 | history | suggested | user133478 | CC BY-SA 4.0 |
English and clarity
|
| Aug 26, 2022 at 8:42 | review | Suggested edits | |||
| S Aug 26, 2022 at 22:08 | |||||
| Jan 22, 2020 at 13:45 | comment | added | user702846 | @abhishek I found your answer is a bit counter intuitive - how GRU "without having memory unit" can have a better performance - perhaps I should read the other papers | |
| S Jun 20, 2019 at 14:53 | history | suggested | Nayantara Jeyaraj | CC BY-SA 4.0 |
Trivial changes
|
| Jun 20, 2019 at 11:14 | review | Suggested edits | |||
| S Jun 20, 2019 at 14:53 | |||||
| Jun 10, 2017 at 18:11 | comment | added | tastyminerals | In addition to your answer there is a nice paper evaluating the performance between GRU and LSTM and their various permutations "An empirical exploration of recurrent network architectures" by Google | |
| Oct 17, 2016 at 13:33 | history | answered | Abhishek | CC BY-SA 3.0 |