Difference between revisions of "Thread:Talk:BeepBoop/Awesome enty/reply (20)"
Jump to navigation
Jump to search
(Reply to Awesome enty) |
m |
||
| Line 1: | Line 1: | ||
| − | Also some deep enough model can learn how surfers (without flattening) "surf" hits, just like networks like "Deep Interest Network" used in CTR. However our current use of KNN allows nothing like this. Maybe some end-to-end approach exists for robocode scenario. | + | Also some deep enough model can learn how surfers (without flattening) "surf" hits, just like networks like "Deep Interest Network" used in CTR that learns how users' interest change over time. However our current use of KNN allows nothing like this. Maybe some end-to-end approach exists for robocode scenario. |
| + | |||
| + | My past experiments (shallow NN that does online-learning without pre-training) with end-to-end approach didn't yield anything interesting though. | ||
Latest revision as of 03:03, 23 June 2021
Also some deep enough model can learn how surfers (without flattening) "surf" hits, just like networks like "Deep Interest Network" used in CTR that learns how users' interest change over time. However our current use of KNN allows nothing like this. Maybe some end-to-end approach exists for robocode scenario.
My past experiments (shallow NN that does online-learning without pre-training) with end-to-end approach didn't yield anything interesting though.
