From 80be49d6df243c41a51c0eb971ffa3fc6cc46cf8 Mon Sep 17 00:00:00 2001 From: =?utf8?q?Fran=C3=A7ois=20Fleuret?= Date: Tue, 25 Jun 2024 16:28:23 +0200 Subject: [PATCH] Update. --- report/culture.tex | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/report/culture.tex b/report/culture.tex index 43aaefe..59899c0 100644 --- a/report/culture.tex +++ b/report/culture.tex @@ -229,13 +229,17 @@ present in the original quizzes: just synchronizing the abilities of the models. There may be some additional complexification of quizzes that get accepted by chance. +\item It can be parallelized by dispatching the GPTs across multiples + nodes, and avoiding a quadratic cost by limiting the validation of + the quizzes to a subset of them. + \item The current process to generate new quizzes, which simply samples them at random is very rudimentary and probably not sufficient in a real-data setup. It can probably be supplemented with a MCTS-type search. \item There may be already in the generated quizzes some structure - that \textemph{we} do not pick up (e.g. certain color or motion + that \emph{we} do not pick up (e.g. certain color or motion patterns). \end{itemize} -- 2.20.1