ClaimsGary Marcus

“Adversarial examples show neural nets don't understand compositional structure of the physical world”

Gary Marcus 16 November 2021 Post by @GaryMarcus on X, 2021-11-16 (X)

Not checkable

Adversarial examples show neural nets don't understand compositional structure of the physical world

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

Gary Marcus, “Adversarial examples show neural nets don't understand compositional structure of the physical world” (said 16 November 2021). Verdict: not checkable. Reliability API, claim c_55ac24ecc49f, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_55ac24ecc49f

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

Reply to this claim

For Gary Marcus, 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.