3,135 articles
Microscopic traffic simulation
Microscopic traffic simulation is a computational method that models each vehicle on a road network individually, computing its position, speed, and driving decisions second by second.
Microsimulation
Microsimulation is a modeling method that simulates individual units one at a time and aggregates results into population-level estimates, proposed by Guy Orcutt in 1957.
Microsoft AI for Earth
Microsoft AI for Earth is a Microsoft grant program, launched in 2017, that provides cloud computing and AI tools for climate, agriculture, biodiversity, and water projects.
Microsoft OneLake
Microsoft OneLake is the unified, tenant-wide SaaS data lake built on Azure Data Lake Storage Gen2 that ships with every Microsoft Fabric tenant, storing Delta Parquet and Iceberg tables and using shortcuts, mirroring, and OneLake security for zero-copy analytics and AI.
Microsoft Research
Microsoft Research, founded by Microsoft in 1991 under first director Rick Rashid, is the company's industrial research organization, conducting basic and applied computer science research at laboratories worldwide.
Microsoft SQL Server
Microsoft SQL Server (MSSQL) is a relational database management system developed by Microsoft, using Transact-SQL and sold in editions from a free Express tier to Enterprise, holding about 33 percent of the on-premises DBMS market.
Million Song Dataset
The Million Song Dataset (MSD) is a free research dataset of audio features and metadata for one million popular music tracks, created by The Echo Nest and LabROSA.
Milvus (vector database)
Milvus is an open-source, cloud-native vector database developed by Zilliz and hosted by the LF AI & Data Foundation, built for fast similarity search over billions of embeddings of text, images, and audio.
Min-max heap
A min-max heap is a complete binary tree, stored in an array, whose alternating min and max levels allow both smallest and largest elements to be accessed quickly.
MinHash
MinHash, or minwise hashing, is a technique for estimating the Jaccard similarity of two sets, introduced by Andrei Broder at DEC in the 1990s to detect near-duplicate documents on the web.
MiniLM
MiniLM is a family of small pre-trained Transformer language models created by Microsoft Research through deep self-attention distillation from teachers like BERT, retaining over 99% of teacher accuracy with half the parameters.
Minimax
Minimax, also known as the minimax algorithm or maximin criterion, is a decision principle minimizing maximum possible loss, used in zero-sum game search and proved for game theory by von Neumann in 1928.
Minimax optimization
Minimax optimization seeks a saddle point where one player minimizes a shared objective and an adversary maximizes it, the formal language of GANs and robust learning.
Minimum cut
A minimum cut, also called min cut, is the cheapest partition of a graph's vertices into two sets, central to network flow through the max-flow min-cut theorem.
Minimum description length
The minimum description length (MDL) principle is a principle of inductive inference in statistical learning that selects the model compressing the data most effectively, balancing fit against complexity.
Minimum spanning tree
A minimum spanning tree is a subset of edges that connects all vertices of a weighted, undirected graph with no cycles and the least total weight; Kruskal's and Prim's algorithms compute it.
Minimum-cost flow problem
The minimum-cost flow problem seeks the cheapest feasible flow through a directed network with arc costs and capacity limits, generalizing shortest path, transportation, and assignment problems.
Minor Planet Center
The Minor Planet Center (MPC) is the official clearinghouse for observations and orbits of minor planets, comets, and natural satellites, operating at the Smithsonian Astrophysical Observatory in Cambridge, Massachusetts.
MIP (complexity)
MIP is the complexity class of decision problems verifiable by a probabilistic polynomial-time verifier interacting with non-communicating provers, shown equal to NEXP by Babai, Fortnow, and Lund in 1991.
Mispronunciation detection
Mispronunciation detection (MDD) is a speech processing method that automatically identifies mispronounced words or phonemes in a learner's speech, mainly for computer-assisted pronunciation training in language learning.
MIT Artificial Intelligence Laboratory
The MIT Artificial Intelligence Laboratory, or AI Lab, was an MIT research laboratory founded in 1959 by John McCarthy and Marvin Minsky that merged into CSAIL in 2003.
MIT Media Lab
The MIT Media Lab, also known as the MIT Media Laboratory, is an interdisciplinary research laboratory at MIT, founded in 1985 by Nicholas Negroponte and Jerome Wiesner.
Mixed-initiative interaction
Mixed-initiative interaction is a strategy from 1990s human-computer interaction research in which humans and computers each take the initiative at different times as a task unfolds.
Mixed-integer nonlinear programming
Mixed-integer nonlinear programming (MINLP), or integer nonlinear programming, is an optimization method for nonlinear problems in which some variables are restricted to integer values, making it NP-hard.
Mixture density network
A mixture density network is a neural network that outputs the parameters of a Gaussian mixture, modeling a full conditional probability distribution rather than a single point estimate.
Mixture of experts
Mixture of experts is a neural network architecture that routes each input to a few specialized expert sub-networks, allowing very large parameter counts with low per-token compute.
Mixup (machine learning)
Mixup is a data augmentation technique that trains a machine learning model on convex combinations of pairs of training examples and their labels, improving generalization and robustness.
MLOps
MLOps, or machine learning operations, is a methodology extending DevOps principles to the machine learning lifecycle, automating model building, deployment, monitoring, and retraining in production.
MMDetection
MMDetection is an open-source object detection toolbox and benchmark built on PyTorch by OpenMMLab, originating from the winner of the COCO Challenge 2018 detection track and covering detection, instance segmentation, and panoptic segmentation.
MNIST database
The MNIST database, or MNIST dataset, is a collection of 70,000 grayscale images of handwritten digits serving as a standard machine learning benchmark since the late 1990s.