alt Hacker NewsYou can train DL models on anything. If you get accurate results then that is maybe publish-worthy.
In this particular case, it is not.
You can train DL models on anything. If you get accurate results then that is maybe publish-worthy.
In this particular case, it is not.
How do you determine if something is publish worthy? If someone puts in a lot of effort experimenting with something that fails, it can still seem publish worthy so others can learn what works and what doesn't. It should be more about level of effort I think. Otherwise the incentives become all wrong too.