Equation 4 · Part 2 · How a Model Actually Gets Small Enough to Run on a Phone

Symbol z

\sigma(z)_i = \frac{\exp(z_i / T)}{\sum_j \exp(z_j / T)}

z

What this part means

z is an argument of the function-like quantity on the left; its role is set by that function’s stated inputs.

Its job in the formula

z is an argument of the function-like quantity on the left; its role is set by that function’s stated inputs.

Full expressionSymbol zArticle meaning

The passage around this formula

Distillation recovers it by training the small “student” network against the large “teacher” network’s full output distribution rather than against the label alone. Write the teacher’s and student’s pre-softmax outputs for a given input as $z_t$ and $z_s$ . A softmax with a temperature T is $\sigma(z)_i = \frac{\exp(z_i / T)}{\sum_j \exp(z_j / T)}$ . At T=1 this is the ordinary softmax used for prediction. Raising T flattens the distribution, pulling the small probabilities assigned to wrong classes up toward visibility, which is exactly the dark knowledge the method wants to expose. The training objective blends two terms: ordinary cross-entropy against the true label, and a match between the student’s and teacher’s…

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 article section

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