AI glossary: terms starting with N

27 terms starting with N, each defined the way the lesson that teaches it uses it, with a link to every lesson where it appears.

__name__

A module's name; "__main__" for the file being run. if __name__ == "__main__": guards the lines that should run only when the file is run.

Taught in
namespace

The table of names that exist, each with a reference to an object.

Taught in
nan

"not a number", the result of an undefined operation such as inf / inf

Example: np.exp(1000) / np.exp(1000)

Taught in
nat

Unit produced when information is measured with natural logarithms.

Taught in
natural log ln

the logarithm with base e

Example: ln 0.5 = −0.6931

Taught in
nearest neighbor

The row with the smallest distance to a given row.

Taught in
negative log likelihood

Log likelihood multiplied by minus one.

Taught in
nested cross-validation

An outer cross-validation that scores a whole search run inside each outer fold.

Taught in
nested dictionary

A dictionary whose values are dictionaries: cafe["drinks"]["Juice"].

Taught in
nested loop

A loop inside the body of another loop. The inner loop runs in full for every iteration of the outer one.

Taught in
nesting

A block inside another block, such as an if inside an if. Each level is indented four more spaces.

Taught in
Newton's method

repeatedly jump to the minimum of the local parabola, x − f′/f″

Example: three steps to −0.351734

Taught in
None

No value. The only value of the type NoneType: rating = None for an order not rated yet, which is different from a rating of 0.

Taught in
NoneType

The type whose only value is None. type(None) gives <class 'NoneType'>.

Taught in
nonlocal

A declaration that assignments use a binding in an enclosing function scope, rather than creating a local binding.

Taught in
nonresponse

A selected person's requested data are not obtained.

Taught in
norm

a length of a vector |

Taught in
normal approximation

Using a normal model where observed shape is close enough for a stated purpose.

Taught in
normal distribution

Symmetric distribution specified by mean and SD.

Taught in
normal equations

AᵀAx̂ = Aᵀb, from the residual being perpendicular to every column

Example: [[3, 3], [3, 5]] x̂ = (6, 7)

Taught in
normal error shape

A model assumption about conditional errors around fitted values.

Taught in
normal quantile

Value at a stated cumulative probability in a normal model.

Taught in
normal vector

a vector perpendicular to a line or plane; here w

Example: (1, 2)

Taught in
notebook

A document made of cells. A code cell holds Python that can run; a text cell holds notes. Jupyter notebook files end in .ipynb.

Taught in
Numerator

the trips that meet the condition.

Taught in
numerical

A column whose values are amounts; continuous when any value in a range is possible, discrete when it counts.

Taught in
numerically stable

computed so that rounding, overflow and underflow do not change the answer

Example: log_expit(-1000) → −1000.0

Taught in