|
|
|
|
|
|
by sriku
728 days ago
|
|
|
Part of the challenge I understood to be learning priors from the training set that can then be applied to an extended private test set. This approach doesn't seem to do any such "learning" on the go. So, supposing it accomplished 85% on the private test set, would it be construed to have won the prize with "we have AGI" being trumpeted out? |
|
|