|
|
|
|
|
|
by TheDudeMan
815 days ago
|
|
|
Same sentiment here. Love the question, but transformers are still so new and so effective that they will probably dominate for a while. We (humans) are following the last thing that worked (imagine if we could do true gradient decent on the algorithm space). Good question, and I'm interested to hear the other responses. |
|
|
They're mostly easy grant money and are being gamed by entire research groups worldwide to be seen as effective on the published papers. State of academia...