The energy loss only works with architectures where pushing down the correct answer's energy automatically raises the energies of other answers.
Not researched Checkable, but outside the sample that was researched.
Factual: Statements about the present or the past, checked against the record: did they hold up?
Cite this claim
Yann LeCun, “The energy loss only works with architectures where pushing down the correct answer's energy automatically raises the energies of other answers.” (said 2006). Verdict: not researched. Reliability API, claim c_6c631037228b, method 0.1.0+c876030c, dataset release v1.1.2. https://epistacklabs.com/claims/c_6c631037228b
This claim is in dataset release v1.1.2, with the same verdict.
Reply to this claim
More factual claims by Yann LeCun
-
Mostly true
“The notions of partition functions, entropy, free energy, variational methods etc, that are so prevalent in the graphical models literature all come from statistical physics.”
-
Mostly true
“No one uses generalization bounds to do model selection.”
No one uses generalization bounds to do model selection; practitioners use cross-validation.
-
Resolved true
“The idea is rooted in Hubel and Wiesel’s classic 1962 work on the cat’s primary visual cortex.”
-
Resolved true
“This loss is always positive, since the second term is a lower bound on the first term.”
-
Resolved false
““Those agents are doing exactly what they’ve been asked to do,” LeCun said.”
Verdicts are made automatically; how verdicts are made.