Matrix regularization - Matrix regularization is the use of penalties or constraints to control the structure of a matrix estimated from data.
Matrix semantics - Matrix semantics is the discipline of keeping track of what the rows, columns and cells of a data matrix mean: which axis is which entity, in which units...
MAUVE (metric) - MAUVE is a measure for comparing two collections of generated and reference examples, developed for evaluating open-ended text generation.
Maximum inner-product search - Maximum inner-product search is the task of finding the stored vector with the largest dot product with a query vector.
Means - ends analysis - Means - ends analysis is a problem-solving strategy that compares the current situation with a desired goal, identifies an important difference and chooses...
Medoid - A medoid is an actual member of a group of observations chosen to minimize the total dissimilarity to the other members.
Memory map - A memory map is a file-access technique where a file on disk is mapped directly into a program's address space, so the program reads and writes it like...
Meta-learning - Meta-learning, often called learning to learn, is training a model on many tasks so it adapts to a new task from very few examples, rather than starting...
Meta-optimization - Meta-optimization is the use of an optimization process to improve the configuration or behavior of another optimization process.
Mini-batch - A mini-batch is the small slice of training data, commonly 32 to a few thousand examples, used for each weight update instead of the whole dataset or a...
Minimum Message Length - Minimum Message Length is a model-selection principle from information theory: the best model is the one that gives the shortest total description of the...
Minority class - The minority class is the rare outcome in a classification dataset: the few fraud cases among millions of honest ones, the few churners among loyal...
Missing values - Missing values are the empty cells in a dataset: measurements never taken, questions never answered, sensors that failed, customers who skipped a field...
Mixture of subspaces - A mixture of subspaces is a modeling approach that treats high-dimensional data as points drawn from several lower-dimensional flat regions, each cluster...
Modality - A modality is a channel or type of data: text, images, audio, video, tables of numbers, sensor readings.
Mode collapse - Mode collapse is a failure of a generative model to represent enough of the variety in its target distribution.
Modes of variation - Modes of variation describe systematic ways observations differ around an average pattern.
Momentum - Momentum is a training technique that lets an optimizer keep moving in its recent direction: each update blends the new gradient with a running average of...
Monolithic Machine Learning Pipeline - A monolithic machine learning pipeline is one built as a single welded unit: ingestion, cleaning, features, training and serving inside one program, so any...
Monte Carlo integration - Monte Carlo integration estimates an integral or average by random sampling: draw points at random, evaluate the quantity at each, and let the sample...
Moral graph - A moral graph is an undirected graph constructed from a directed acyclic graph by connecting every pair of nodes that share a child and then removing arrow...
Moral outsourcing - Moral outsourcing is the shifting of responsibility for ethical judgment or harmful consequences onto an external person, organization or system.
Multi-class - Multi-class describes a classification setting where each item belongs to exactly one of three or more categories: a ticket routed to one of ten teams, a...
Multi-class classification - Multi-class classification is the task of assigning each item to exactly one category from three or more: routing a ticket to one of ten teams, tagging a...
Multi expression programming - Multi expression programming is an evolutionary programming method that represents several candidate expressions within one linear chromosome.
Multi-label - Multi-label describes a setting where each item can carry several labels at once: a photo tagged beach and sunset and family, a ticket marked billing and...
Multi-label classification - Multi-label classification is the task of assigning each item a set of labels, from zero to many: tagging a document with all its topics, flagging a...
Multi-task Elastic-Net - Multi-task Elastic-Net is a regression method that learns several related prediction tasks together, mixing two penalties so the tasks share a common set of...
Multi-task Lasso - Multi-task Lasso is a regression method that learns several related tasks together under a shared sparsity penalty: a field is kept or evicted for the whole...
Multiclass-multioutput classification - Multiclass-multioutput classification is the setting where each item must be assigned one class in each of several independent category systems at once: a...
Multidimensional analysis - Multidimensional analysis examines data through several variables, attributes or perspectives at once.
Multilinear principal component analysis - Multilinear principal component analysis is a dimensionality-reduction method that learns compact representations of tensor-shaped data through projections...
Multilinear subspace learning - Multilinear subspace learning is a family of methods that learn lower-dimensional representations directly from tensor-shaped observations.
Multimodal representation learning - Multimodal representation learning develops numerical representations from more than one kind of data, such as text, images, audio or video.
Multimodal sentiment analysis - Multimodal sentiment analysis estimates expressed positive, negative or other sentiment using more than one kind of input, such as words, vocal...
Multinomial logistic regression - Multinomial logistic regression is a statistical classification model for outcomes with more than two unordered categories.
Multiple correspondence analysis - Multiple correspondence analysis is an exploratory method for summarizing associations among several categorical variables.
Multiple discriminant analysis - Multiple discriminant analysis uses several measured variables to distinguish among known groups, commonly by constructing linear combinations that...
Multiplicative weight update method - The multiplicative weight update method is an iterative decision-making framework that maintains weights over alternatives and changes each weight by...
Multispectral pattern recognition - Multispectral pattern recognition identifies or groups objects and regions using measurements from several wavelength bands.
Multitask - Multitask describes learning several related tasks together in one model: one representation, several output heads, so each task borrows evidence from the...
Multivariate adaptive regression spline - A multivariate adaptive regression spline model represents a response as a weighted combination of simple piecewise functions chosen from the data.
N-gram - An N-gram is a sequence of N consecutive items from text, usually words: 'the cat' is a bigram, 'the cat sat' a trigram, and counting such sequences is the...
Native-language identification - Native-language identification is the task of estimating a writer's or speaker's first-language background from language they produce, often in a second...
Natural language processing - Natural language processing is the field of getting computers to work usefully with human language: reading, classifying, translating, summarizing and...
Natural language understanding - Natural language understanding is the branch of NLP concerned with machine comprehension: turning what people write or say into structured meaning a system...
Nearest Centroid Classifier - Nearest Centroid Classifier is one of the simplest classifiers that exists: compute the average example of each class, the centroid, and assign any new item...
Nearest neighbor - Nearest neighbor methods classify or predict an item by finding the most similar examples in the training data and borrowing their answers: the majority...