/AI1d ago

NYU's Andrew Gordon Wilson argues that demands for a unifying deep learning theory are biased by researchers' preferred frameworks

Researchers rarely accept theories outside their preferred mathematical languages.

--0--
Original posts
Reposts
Original post
Andrew Gordon Wilson@andrewgwils#148inAI

When someone says "we need theory of deep learning", note that probably nothing will "count" as a theory of deep learning unless it is *their* theory, or unless it is speaking a language, and using techniques, that they already have a bias towards.

9:44 PM · Jun 2, 2026 · 13.8K Views
Sentiment
Sentiment building, check back later.
Cluster Engagement
-
Views
-
Comments
-
Reposts
-
Bookmarks
Expand data
Posts from X
Most Activity
Most ActivityTimeline
RETWEETS14

When someone says "we need theory of deep learning", note that probably nothing will "count" as a theory of deep learning unless it is *their* theory, or unless it is speaking a language, and using techniques, that they already have a bias towards.

1dViews 13.8KLikes 218Bookmarks 37