ClaimsYann LeCun

“More importantly, the very reason for internally normalizing HMMs and Bayesian nets is somewhat contradictory with the idea of training them discriminatively.”

Yann LeCun 2006 A Tutorial on Energy-Based Learning (yann.lecun.com) archived copy

Not checkable

More importantly, the very reason for internally normalizing HMMs and Bayesian nets is somewhat contradictory with the idea of training…

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, “More importantly, the very reason for internally normalizing HMMs and Bayesian nets is somewhat contradictory with the idea of training…” (said 2006). Verdict: not checkable. Reliability API, claim c_6b6593c5102a, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_6b6593c5102a

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.