Maths for ML / Notation

e^{x},\ \exp(x)

exponential

FunctionsBeginner

Say it “e to the x”

Raises e (≈ 2.718) to the power x. Always positive; grows very fast.

Example

e^{0} = 1

In code

np.exp(x)

torch.exp(x)

Where you’ll see it in ML

Softmax and sigmoid are built from exp.

Don’t confuse it with

$\log x,\ \ln x$ logarithm The inverse of exp: what power of the base gives x. In ML papers log almost always means natural log (base e).
$\operatorname{softmax}(\mathbf{z})_i = \frac{e^{z_i}}{\sum_j e^{z_j}}$ softmax Turns a vector of any scores into positive numbers that sum to 1 — a probability distribution.

Lessons that use it

← All 94 symbols