ClaimsYann LeCun

“But contrastive methods have a major issue: They are very inefficient to train.”

Yann LeCun 4 March 2021 Self-supervised learning: The dark matter of intelligence (Meta AI)

Not checkable

But contrastive methods have a major issue: They are very inefficient to train.

Not checkable An opinion, value judgement or statement with nothing to check.

Not checkable: An opinion, value judgement or statement with nothing to check. Not scored.

Cite this claim

Yann LeCun, “But contrastive methods have a major issue: They are very inefficient to train.” (said 4 March 2021). Verdict: not checkable. Reliability API, claim c_d90e37883981, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_d90e37883981

This claim is in dataset release v1.1.2, with the same verdict.

Reply to this claim

For Yann LeCun, or someone speaking for them: a correction or counter-evidence. Replies are read before anything is shown; an approved reply shows your name, role, date, statement and link. Your email address is never shown and is deleted 30 days after the decision (privacy).

Verdicts are made automatically; how verdicts are made.