Artificial intelligence and data

Nonnegative matrix factorization

Nonnegative matrix factorization (NMF) approximates a nonnegative data matrix as the product of two smaller nonnegative matrices, giving additive, parts-based representations used for dimensionality reduction, topic extraction, and source separation.

Normalization (machine learning)

Normalization in machine learning is a family of techniques that rescale a neural network's inputs, activations, or weights during training, making gradient-based optimization faster and more stable.

Normalizing flow

A normalizing flow is a generative model that transforms a simple distribution, usually a standard normal, into a complex one through invertible transformations, so it can both sample and compute exact likelihoods.

Normalizing flows

Normalizing flows are generative models that transform a simple base distribution, typically a Gaussian, into a complex target distribution through invertible transformations, enabling exact density evaluation and efficient sampling.

North American Chapter of the Association for Computational Linguistics

NAACL, the North American Chapter of the Association for Computational Linguistics, is a regional chapter organizing an annual natural language processing conference, renamed Nations of the Americas Chapter in 2024.

NoSQL

NoSQL, or "not only SQL," is an umbrella term for non-relational databases that store data as documents, key-value pairs, wide columns, or graphs, and typically scale horizontally across many servers.

Notch filter

A notch filter is a band-stop filter with a very narrow stopband that rejects a narrow frequency band, such as 50 or 60 Hz mains hum.

Novelty detection

Novelty detection is a machine learning task that scores test samples against a model of normal data, used in fraud detection, medical diagnosis, and fault detection.

NP-completeness

NP-completeness is a property of decision problems that are at least as hard as every problem in NP, first proved for SAT by Stephen Cook in 1971 and extended by Karp's 21 problems in 1972.

NP-hardness

NP-hardness is a property of computational problems to which every problem in NP can be reduced in polynomial time, introduced by Stephen Cook and Leonid Levin in 1971.

NSGA-II

NSGA-II (Non-dominated Sorting Genetic Algorithm II) is a multi-objective evolutionary algorithm introduced by Deb and colleagues in 2002, and the standard first-choice solver for real-world multi-objective optimization.

NSGA-III

NSGA-III is an evolutionary many-objective optimization algorithm introduced by Kalyanmoy Deb and Himanshu Jain in 2013 that maintains diversity using reference points for problems with three or more objectives.

Null (SQL)

Null (SQL), often written NULL, is a special marker for a missing or inapplicable value, introduced by Edgar F. Codd, distinct from zero and the empty string.

Numerical differentiation

Numerical differentiation is the set of methods for estimating a function's derivative from sampled values using finite differences, balancing truncation error and floating-point round-off through the choice of step size.

nuScenes

nuScenes is a public, large-scale autonomous driving dataset developed by Motional, released in full in March 2019 with 1,000 annotated scenes collected in Boston and Singapore.

NVIDIA Earth-2

NVIDIA Earth-2 is a platform of AI models, software libraries, and cloud services developed by NVIDIA for weather forecasting and climate simulation, announced in 2021 as a planned digital twin of Earth.

Nyquist frequency

The Nyquist frequency, also known as the folding frequency or Nyquist limit, is half the sampling rate of a sampled signal, named after engineer Harry Nyquist; frequencies above it alias.

Nyquist rate

The Nyquist rate, also called the Nyquist sampling rate, is the minimum rate for sampling a bandlimited signal, 2B samples per second for bandwidth B, named for Harry Nyquist.

Nyström method

The Nyström method approximates a large kernel matrix by sampling a small subset of columns and reconstructing a low-rank approximation, avoiding the O(n³) cost of exact kernel computations.

NYU Depth V2

NYU Depth V2 is an indoor computer-vision dataset of RGB and depth image pairs captured with a Microsoft Kinect, introduced in 2012 by New York University researchers.

Object database

An object database, also known as an object-oriented database management system (OODBMS), stores programming-language objects directly, so applications read and write objects without converting them to tables and rows.

Object-based image analysis

Object-based image analysis (OBIA), also called geographic object-based image analysis (GEOBIA), is a remote sensing method that segments satellite or aerial imagery into meaningful objects and classifies them instead of individual pixels.

Object–relational mapping

Object–relational mapping (ORM) is a technique that maps data between object-oriented programs and relational databases, with tools like Hibernate, Django ORM, and Prisma generating SQL and writing changes back to the database.

OBO Foundry

The OBO Foundry (Open Biological and Biomedical Ontologies Foundry) is a community-run consortium, set out in a 2007 paper, that coordinates interoperable, openly licensed ontologies for the biological and biomedical sciences.

Octree

An octree is a tree data structure in which each internal node has exactly eight children, recursively subdividing 3-D space into eight subcubes, or octants.

OECD AI Policy Observatory

The OECD AI Policy Observatory (OECD.AI) is an online platform launched by the OECD in Paris in February 2020 to help countries monitor the responsible development of trustworthy artificial intelligence.

Off-policy learning

Off-policy learning is a reinforcement learning approach that evaluates or improves a target policy using data from a different behavior policy, including offline RL from logged data.

Office of the Privacy Commissioner of Canada

The Office of the Privacy Commissioner of Canada (OPC) is the independent federal agency that oversees the Privacy Act and PIPEDA, Canada's federal privacy laws.

Okapi BM25

Okapi BM25, often shortened to BM25, is a ranking function that scores how well a document matches a query, and is the default in Elasticsearch and Lucene.