← All parts of this equation

Equation 8 · Part 1 · How a Model Actually Gets Small Enough to Run on a Phone

Symbol T^2

T2T^2
T2T^2

What this part means

the square of T; tuned as a hyperparameter [ 1 ].

Its job in the formula

T2T^2 is squared: multiply the underlying quantity by itself. The square is a mathematical operation, not a second independent variable.

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

An exponent tells how a base is used in multiplication. In x³, x is the base and 3 is the exponent: x³ = x × x × x.

Open the illustrated exponents: repeated multiplication and powers 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.