Artificial intelligence and data

Moth-flame optimization

Moth-flame optimization (MFO) is a swarm intelligence metaheuristic for numerical optimization, proposed by Seyedali Mirjalili in 2015 and inspired by moths' spiral flight around lights.

Moth-flame optimization algorithm

Moth-flame optimization (MFO) is a population-based metaheuristic for continuous, derivative-free optimization, introduced by Seyedali Mirjalili in 2015, in which candidate solutions called moths move along logarithmic spirals toward flames, the best positions found so far.

Oct 26, 2026

MotherDuck

MotherDuck is a Seattle-founded (2022) serverless cloud data warehouse built on DuckDB, known for hybrid local/cloud query processing, per-user isolated Duckling instances, and about $133 million in total funding led by a16z and Felicis.

Motion compensation

Motion compensation is a video compression technique that predicts each frame from previously coded frames by estimating object motion, transmitting only motion vectors and residuals.

Motion detection

Motion detection is a computer vision method that identifies moving regions or objects in video by analyzing changes between frames, typically producing a binary foreground mask often converted into bounding boxes and motion alarms.

Motion interpolation

Motion interpolation, also known as motion smoothing or video frame interpolation, synthesizes new video frames between existing ones to raise a video's effective frame rate, often causing the soap opera effect on televisions.

Oct 22, 2026

Mott neuromorphic devices

Mott neuromorphic devices are electronic devices for brain-inspired computing that use Mott insulators, whose abrupt metal-insulator transition enables fast, low-energy switching in artificial neurons and synapses.

Movidius Myriad

Movidius Myriad is a family of low-power vision processing units developed by the Irish company Movidius and continued by Intel after its 2016 acquisition, powering drones and Neural Compute Sticks.

MovieLens

MovieLens is a web-based movie recommendation service run by GroupLens Research at the University of Minnesota, launched in 1997, and the source of widely used recommender research datasets.

MP3.com

MP3.com was a San Diego music website founded in 1997 by Michael Robertson, which grew to over 10 million members before copyright lawsuits broke it.

MPI Sintel

MPI Sintel is a public benchmark for evaluating optical flow algorithms, derived from the Blender Foundation's open source animated short film Sintel and presented at ECCV 2012.

MS MARCO

MS MARCO, short for MicroSoft MAchine Reading COmprehension, is a Microsoft collection of datasets built from real Bing queries, released in 2016 to train search and question-answering models.

MSR-VTT

MSR-VTT (MSR Video to Text) is a large-scale open-domain dataset of web video clips paired with natural-language descriptions, released by Microsoft Research in 2016 as a video captioning benchmark.

MTCNN

MTCNN (Multi-task Cascaded Convolutional Networks) is a deep learning framework performing joint face detection and alignment with three cascaded networks, proposed by Kaipeng Zhang and colleagues in 2016.

Multi-agent proximal policy optimization

Multi-agent proximal policy optimization (MAPPO) is a multi-agent reinforcement learning algorithm that extends PPO, using a centralized value function in training and decentralized policies at execution.

Multi-agent system

A multi-agent system (MAS) is a system of autonomous software or robotic agents that coordinate in a shared environment, a field growing out of distributed artificial intelligence.

Multi-armed bandit

The multi-armed bandit (MAB), also called the K-armed bandit, is a sequential decision problem in which an agent must balance exploring new actions against exploiting the best known one.

Multi-document summarization

Multi-document summarization (MDS) is a natural language processing task that produces one summary from a cluster of related documents, resolving redundancy and merging complementary information.

Multi-fidelity Bayesian optimization

Multi-fidelity Bayesian optimization (MFBO) is a method for optimizing expensive black-box functions when cheaper, less accurate approximations, such as low-fidelity simulations, are available, cutting evaluation costs.

Multi-head attention

Multi-head attention is a neural network mechanism, introduced in the 2017 paper Attention Is All You Need, that runs several attention operations in parallel and forms the Transformer's attention layer.

Multi-label classification

Multi-label classification is a supervised machine learning task assigning each instance one or more labels at once, applied to text categorization, gene analysis, and search engines.

Multi-objective Bayesian optimization

Multi-objective Bayesian optimization (MOBO) is a sample-efficient method for optimizing several expensive, competing objectives, returning an approximation of the Pareto front rather than a single optimum.

Multi-objective evolutionary algorithm

A multi-objective evolutionary algorithm (MOEA) is an optimization method that returns a Pareto set approximation, a set of mutually nondominated solutions, rather than a single best point.

Multi-objective evolutionary optimization

Multi-objective evolutionary optimization uses population-based evolutionary algorithms to optimize two or more conflicting objectives at once, seeking trade-off solutions that converge to and evenly cover the Pareto front.

Multi-objective optimization

Multi-objective optimization, also known as Pareto optimization, deals with problems having two or more conflicting objectives optimized simultaneously; the result is a set of trade-off Pareto-optimal solutions.

Multi-objective particle swarm optimization

Multi-objective particle swarm optimization (MOPSO) is a swarm intelligence method that extends particle swarm optimization to conflicting objectives, using an archive of non-dominated solutions to approximate the Pareto front.

Multi-task learning

Multi-task learning (MTL) is a machine learning approach that trains a single model on several related tasks at once over a shared representation, formalized by Richard Caruana in 1993.

Multi-verse optimizer

The multi-verse optimizer (MVO) is a population-based metaheuristic for global optimization, introduced by Seyedali Mirjalili and colleagues in 2015, using white holes, black holes, and wormholes as search operators.

Multi-view clustering

Multi-view clustering is an unsupervised machine learning method that groups objects using several feature representations, or views, of the same data, seeking clusterings consistent across views.