3,135 articles
Neuroevolution
Neuroevolution is a machine learning approach that uses evolutionary algorithms to optimize neural networks, maintaining a population of candidate networks rather than training weights by gradient descent.
Neuroevolution of augmenting topologies
Neuroevolution of augmenting topologies (NEAT) is an evolutionary algorithm introduced by Kenneth Stanley and Risto Miikkulainen in 2002 that evolves both neural network weights and structure, growing from minimal networks.
Neuromorphic computing
Neuromorphic computing is an approach to computation modeled on the structure and function of biological nervous systems, combining event-driven spiking communication with co-located memory and processing for greatly reduced energy use.
Neuromorphic computing with nanoscale spintronic oscillators
Neuromorphic computing with nanoscale spintronic oscillators is a brain-inspired hardware approach using spin-torque and spin Hall nano-oscillators as artificial neurons, first demonstrated experimentally in 2017.
Neuromorphic engineering
Neuromorphic engineering, also known as neuromorphics, is the design of computing hardware and methods inspired by neural computation, using event-driven spiking circuits that promise extremely low power consumption.
Neuromorphic photonics
Neuromorphic photonics is a computing field that uses lasers, modulators, and resonators to perform neural-network functions, aiming at high speed and energy efficiency beyond electronic AI accelerators.
New York City Local Law 144
New York City Local Law 144 is a 2021 ordinance requiring annual bias audits, public results, and candidate notice for automated employment decision tools, the first law of its kind.
Newton's method in optimization
Newton's method in optimization is a second-order iterative algorithm for minimizing a twice-differentiable function, using the gradient and Hessian matrix to form a quadratic model at each step.
NEXP
NEXP, also written NEXPTIME, is the complexity class of decision problems solvable in nondeterministic exponential time; the exponential-time analog of NP, it strictly contains NP, and whether it equals EXP is unknown.
Nextdata (company)
Nextdata is a San Francisco data-mesh startup founded in 2022 by Zhamak Dehghani, who created the data mesh concept at ThoughtWorks in 2018; its Nextdata OS product builds autonomous, containerized data products, backed by a $12M 2023 seed round from Greycroft and Acrew Capital.
Nigeria Data Protection Act
The Nigeria Data Protection Act is a 2023 Nigerian statute governing personal data processing, signed by President Bola Tinubu and enforced by the Nigeria Data Protection Commission.
Nimble (file format)
Nimble (formerly Alpha) is Meta's Apache-2.0 C++ columnar file format, a Parquet/ORC replacement for wide ML tables with thousands of columns, using FlatBuffers metadata, block encoding, and cascading pluggable encodings; experimental, Velox-only, no releases.
NLTK
NLTK, the Natural Language Toolkit, is a free, open-source Python library for natural language processing. It was created in 2001 at the University of Pennsylvania as teaching courseware.
No free lunch theorem
The no free lunch (NFL) theorem is a 1997 mathematical result by Wolpert and Macready stating that averaged over all possible objective functions, all search algorithms perform equally well.
No Language Left Behind
No Language Left Behind is a Meta AI machine translation project announced in 2022 whose NLLB-200 model translates directly between 200 languages, including many low-resource African and Indian languages.
No-regret learning
No-regret learning is an online decision-making method where a player repeatedly chooses actions against unknown losses, with regret growing sublinearly, dating to work by Hannan and Blackwell in the 1950s.
Node2vec
Node2vec is a graph embedding method that learns a low-dimensional vector for every node in a network by simulating biased random walks and training skip-gram on them.
Noise injection (machine learning)
Noise injection is a machine learning regularization technique that deliberately adds random perturbations to a model's inputs, weights, gradients, or activations during training to reduce overfitting.
Noise level estimation
Noise level estimation is a signal and image processing method that measures the strength of noise in data from noisy observations alone, without a clean reference.
Noise shaping (computation)
Noise shaping (computation), also known as stochastic rounding, randomly maps numbers to maintain zero-mean error, limiting accumulated error growth to the square root of $n$.
NOMAD Laboratory
The NOMAD Laboratory, established in 2014 in Berlin, is a German research group operating NOMAD, an open-source platform making materials science data FAIR and reusable.
NOMAD Repository
The NOMAD Repository is an open repository for computational materials-science data, launched in 2014 by the NOMAD Laboratory as the first FAIR storage infrastructure for materials simulations.
Non-blocking algorithm
A non-blocking algorithm, also called non-blocking synchronization, is a concurrent algorithm in which a delayed or failed process cannot prevent others from completing, typically built from atomic primitives like compare-and-swap.
Non-dominated sorting genetic algorithm
The non-dominated sorting genetic algorithm (NSGA) is a family of multi-objective evolutionary algorithms, introduced by Srinivas and Deb in 1994, that evolves a whole set of trade-off solutions in one run.
Non-local means
Non-local means (NL-means) is an image denoising algorithm introduced by Buades, Coll, and Morel in 2005, which estimates each pixel from similar patches found anywhere in the image.
Nondeterministic algorithm
A nondeterministic algorithm, also called nondeterministic computation, is a theoretical algorithm with multiple possible steps that always takes the right or best one, underlying the class NP.
Nonlinear dimensionality reduction
Nonlinear dimensionality reduction is a family of machine learning methods that convert high-dimensional data into low-dimensional representations while preserving curved manifolds and neighborhoods, used for visualization and clustering.
Nonlinear filtering
Nonlinear filtering, or nonlinear filtering theory, is the recursive Bayesian estimation of a hidden system state from noisy, partial observations, solved approximately by methods like the particle filter.
Nonlinear model reduction
Nonlinear model reduction is a family of computational methods that builds low-dimensional approximate models of high-dimensional nonlinear dynamical systems, typically by projecting the full model onto a low-dimensional subspace, enabling fast simulation, optimization, and real-time control.
Nonlinear system identification
Nonlinear system identification is the construction of mathematical models of nonlinear dynamical systems from measured input and output data, using structures such as NARMAX, block-oriented, and neural state-space models.