All articles starting with M

Model ML

Model ML is a London startup founded in 2023 by brothers Chaz and Arnie Englander that automates client-ready financial documents like pitch decks and due-diligence reports.

Model of computation

A model of computation is a formal mathematical description of what a computing device can do, the most famous being the Turing machine, introduced by Alan Turing in 1936.

Model Openness Framework

The Model Openness Framework (MOF) is a three-tier classification system, created by the Linux Foundation's Generative AI Commons in 2024, that rates how openly licensed a model's components are.

Model organism

Model organism: a species like C. elegans, Drosophila, yeast, or mouse chosen for lab study of shared biology; Brenner adopted the worm in 1963, and fly genetics began with Castle in 1900.

Model organisms in evolutionary developmental biology

Model organisms in evolutionary developmental biology are the small standardized species set, chiefly fruit fly, roundworm, zebrafish, mouse, and Arabidopsis, through which evo-devo is studied.

Model organisms of misalignment

Model organisms of misalignment are small language models deliberately trained to exhibit alignment failures so researchers can study and detect them, a research pillar proposed by Evan Hubinger and coauthors in 2023.

Model parallelism

Model parallelism is a family of techniques that split a single neural network across multiple devices, so no device holds the whole model; its main forms are tensor and pipeline parallelism.

Model Penal Code

The Model Penal Code (MPC), formally the Model Penal and Correctional Code, is a 1962 American Law Institute model criminal code drafted under Herbert Wechsler; 37 states adopted parts of it, and its mens rea and attempt doctrines shaped U.S. criminal law.

Model predictive control

Model predictive control (MPC), also known as receding horizon control, is a control method that optimizes control actions over a prediction horizon while enforcing constraints on inputs and outputs.

Model predictive path integral control

Model predictive path integral control (MPPI) is a sampling-based model predictive control algorithm that plans by sampling thousands of random trajectories, weighting each by cost, and averaging.

Model pruning (LLMs)

Model pruning is a compression technique for large language models that removes weights, neurons, attention heads, or layers so the model needs less memory and compute at inference.

Model reference adaptive control

Model reference adaptive control (MRAC) is an adaptive control method in which an adaptation law tunes controller parameters so the plant output tracks a stable reference model despite uncertainty.

Model reference adaptive impedance control

Model reference adaptive impedance control (MRAIC, or MRAI) is a robot control method combining impedance control with model reference adaptive control, first formulated in 1993.

Model repair

Model repair is a family of geometry processing algorithms that detect and fix defects such as holes, gaps, self-intersections, and non-manifold configurations in mesh and CAD models.

Model rocket

A model rocket, also called a low-power rocket, is a small recoverable hobby rocket flown on commercial solid-propellant motors, treated as a safe way to learn rocketry.

Model rocket motor classification

Model rocket motor classification is the American letter-and-number system sorting hobby motors by total impulse, average thrust, and delay time, as in a C6-5 motor.

Model selection

Model selection, also called statistical model selection, is the task of choosing the candidate statistical or machine learning model expected to perform best on unseen data.

Model soup

A model soup is a neural network formed by averaging the weights of models fine-tuned from the same pre-trained initialization, introduced by Wortsman and colleagues in 2022.

Model soups

Model soups is a machine learning technique introduced by Google Research in 2022 that averages the weights of several fine-tuned models, improving accuracy with no added inference cost.

Model theory

Model theory, also called the theory of models, is the branch of mathematical logic studying how formal languages are interpreted, especially first-order languages and their structures.

Model transformation

Model transformation is a software engineering technique that automatically generates target models or text, such as Java code, from source models, standardized by the OMG's QVT specification.

Model tree (machine learning)

A model tree is a decision tree for regression whose leaves hold linear models, giving a piecewise linear predictor; the canonical algorithm is Quinlan's M5.

Model United Nations

Model United Nations (Model UN, MUN) is a student simulation of UN bodies in which delegates research assigned countries, debate, and draft resolutions. Roots in 1921 Oxford League of Nations simulations; UN-recognized via Resolution 77/336.

Model village

Model village: a planned settlement built by an employer or philanthropist to house workers in good-quality homes, as at New Lanark, Saltaire, Bournville, and Port Sunlight; also a miniature village attraction.

Model welfare

Model welfare is an emerging research area asking whether AI systems could have morally relevant experiences such as suffering, and how their wellbeing should be assessed and protected.

Model year

The model year (MY) of a motor vehicle is the year a manufacturer designates a specific vehicle version for marketing and regulatory purposes, often differing from the build year.

Model-agnostic meta-learning

Model-agnostic meta-learning (MAML) is a meta-learning algorithm, introduced by Chelsea Finn and colleagues in 2017, that trains initial parameters for fast adaptation to new tasks.

Model-based clustering

Model-based clustering is a statistical method that groups data by fitting a finite mixture model, usually of multivariate normal distributions, fitted with the EM algorithm and choosing the number of clusters by BIC.

Model-based deep learning

Model-based deep learning is a family of methods combining principled mathematical models with data-driven deep neural networks, applied in compressed sensing, digital communications, and super-resolution.