Love, BC;
Mok, RM;
(2023)
You can't play 20 questions with nature and win redux.
Behavioral and Brain Sciences
, 46
, Article e402. 10.1017/S0140525X23001747.
Preview |
Text
bowersCommentaryFull.pdf - Accepted Version Download (64kB) | Preview |
Abstract
An incomplete science begets imperfect models. Nevertheless, the target article advocates for jettisoning deep-learning models with some competency in object recognition for toy models evaluated against a checklist of laboratory findings; an approach which evokes Alan Newell's 20 questions critique. We believe their approach risks incoherency and neglects the most basic test; can the model perform its intended task.
Archive Staff Only
 |
View Item |
