← All parts of this equation

Equation 11 · Part 1 · How a Model Actually Gets Small Enough to Run on a Phone

Symbol T

TT
TT

What this part means

tuned as a hyperparameter [ 1 ].

Its job in the formula

T is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.

Where the article explains it

Hinton and colleagues note that because the magnitude of the gradients produced by the soft-target term scales as 1/T2T^2 , multiplying the term by T2T^2 keeps the relative contribution of the two loss terms roughly stable as T is tuned as a hyperparameter [ 1 ] .

The passage around this formula

The T2T^2 factor is not decorative. Hinton and colleagues note that because the magnitude of the gradients produced by the soft-target term scales as 1/T2T^2 , multiplying the term by T2T^2 keeps the relative contribution of the two loss terms roughly stable as T is tuned as a hyperparameter [ 1 ] . Without it, raising the temperature to expose more dark knowledge would simultaneously and silently shrink the gradient signal doing the exposing.

Read this part in the article →

Learn the underlying idea

A variable is a named place for a value. Its letter is a local label: x can mean position in one formula and a data point in another.

Open the illustrated variables: a letter stands for a value guide →

See this notation across published equations →

Sources cited in the surrounding passage

These citations provide research context; check each source for the exact claim it supports.