Maths for ML / Notation

\mu

mu (mean)

Greek letters and conventionsBeginner

Say it “mu”

Conventionally the mean of a distribution.

Example

\mu = \mathbb{E}[X]

In code

x.mean()

x.mean()

Where you’ll see it in ML

BatchNorm/LayerNorm subtract μ; VAEs predict μ.

Don’t confuse it with

$\bar{x}$ bar Usually the mean (average) of x. Occasionally a complex conjugate.
$\mathbb{E}_{x\sim p}[f(x)]$ expectation The average value you'd get if you sampled many times — weighted by probability.
$\mathcal{N}(\mu, \sigma^2)$ normal (Gaussian) distribution The bell curve, set by a mean μ and a variance σ².

← All 94 symbols