aiwiki.page
English
Home / Category

Computer Science

1034 entriesPage 11 of 18

Subcategories

All entries in Computer Science

Metal–Oxide–Semiconductor Field-Effect Transistor

A MOSFET is an insulated-gate transistor that controls semiconductor conduction through an electric field, enabling electronic switching, amplification, and integrated circuits.

mosfet
Metaprogramming

Metaprogramming treats programs as data that other programs can inspect, generate, transform, or specialize.

metaprogramming
Microdata (HTML)

Microdata is an HTML mechanism for embedding machine-readable descriptions of entities and their properties within web pages.

microdata-html
Microkernel

A microkernel is an operating-system architecture that keeps privileged mechanisms small and implements most services in isolated user-space components.

microkernel
Micron Technology

Micron Technology is an American semiconductor company that develops and manufactures memory chips and data-storage products for computing, communications, automotive, and industrial applications.

micron-technology
Microprocessor

A microprocessor is an integrated electronic processor that executes machine instructions, providing programmable computation in devices ranging from embedded controllers to supercomputers.

microprocessor
Microsoft Windows

Microsoft Windows is a family of proprietary operating systems, from the MS-DOS-based graphical shell of 1985 to the NT-based Windows 11, used on PCs, servers and embedded devices.

microsoft-windows
Minimax

Minimax is an adversarial search algorithm that selects a move by optimizing its outcome against an opponent assumed to play optimally.

minimax
MLOps

MLOps is the engineering discipline for developing, deploying, monitoring, and governing machine-learning systems throughout their operational life cycle.

mlops
Mobile Phone

A mobile phone is a portable handheld device that communicates over cellular radio networks. It has evolved from bulky 1980s handsets into multipurpose smartphones.

mobile-phone
Model Checking

Model checking automatically determines whether a mathematical model of a system satisfies formally specified properties by systematically analyzing its possible behaviors.

model-checking
Model collapse

Model collapse is the progressive loss of fidelity or diversity that can occur when machine-learning models are repeatedly trained on earlier models’ outputs.

model-collapse
Model Context Protocol

Model Context Protocol is an open protocol that standardizes how artificial intelligence applications discover and use external tools, data sources, and reusable prompts.

model-context-protocol
Model of Computation

A model of computation formally specifies how computational processes operate, what they can compute, and which resources they consume.

model-of-computation
Monolithic Kernel

A monolithic kernel places core operating-system services in a shared privileged execution environment, enabling direct interaction between subsystems but providing limited fault isolation within the kernel.

monolithic-kernel
Monte Carlo Algorithm

A Monte Carlo algorithm uses randomness to achieve a bounded computational cost while allowing a controlled probability of an incorrect result.

monte-carlo-algorithm
Monte Carlo Dropout

Monte Carlo dropout estimates neural-network predictive uncertainty by retaining dropout during inference and aggregating predictions from repeated stochastic forward passes.

monte-carlo-dropout
Monte Carlo Tree Search

Monte Carlo tree search is a planning method that incrementally builds a search tree using sampled outcomes to guide computational effort toward promising decisions.

monte-carlo-tree-search
Moonshot AI

Moonshot AI is a Beijing-based artificial intelligence company founded in 2023 that develops the Kimi chatbot and a family of large language models, several released with open weights.

moonshot-ai
Moore's Law

Moore’s law describes the historical exponential growth of integrated-circuit complexity and its role in semiconductor technology, economics, and computing.

moores-law
Multi-head Attention

Multi-head attention combines parallel attention computations with distinct learned projections to represent multiple relationships within or between sequences.

multi-head-attention
Multi-query Attention

Multi-query attention is a Transformer attention variant that shares keys and values across query heads, reducing memory requirements and data movement during autoregressive generation.

multi-query-attention
Multi-task Learning

Multi-task learning trains related predictive tasks together, sharing information to improve generalization, data efficiency, or computational efficiency.

multi-task-learning
Multiclass Classification

Multiclass classification is a machine-learning task that assigns each input to exactly one of three or more predefined classes.

multiclass-classification
Multicloud

Multicloud is the use of cloud services from multiple providers, whether for separate workloads or as parts of an integrated computing environment.

multicloud
Multifactor Authentication

Multifactor authentication verifies identity using distinct categories of evidence, reducing dependence on passwords while introducing requirements for secure enrollment, recovery, and operation.

multifactor-authentication
Multilabel Classification

Multilabel classification is a machine-learning task in which each example may be assigned multiple labels from a predefined set, rather than exactly one mutually exclusive class.

multilabel-classification
Multilayer Perceptron

A multilayer perceptron is a feedforward neural network that learns nonlinear mappings through successive layers of weighted connections and activation functions.

multilayer-perceptron
Multimodal Learning

Multimodal learning develops machine-learning systems that relate or combine information from different forms of data, such as text, images, audio, and video.

multimodal-learning
Multiple Patterning

Multiple patterning is a family of semiconductor fabrication techniques that combines several patterning steps to produce features too closely spaced for a single lithographic exposure.

multiple-patterning
Multiplexing

Multiplexing enables multiple signals, data streams, or activities to share a communication channel or computing resource while preserving their separate identities.

multiplexing
Muon optimizer

Muon is a neural-network optimizer that transforms momentum updates for matrix-valued weights using approximate orthogonalization, typically computed with Newton–Schulz iterations.

muon-optimizer
Mustafa Suleyman

Mustafa Suleyman is a British technology entrepreneur, DeepMind and Inflection AI co-founder, author, and Microsoft AI executive.

mustafa-suleyman
Mutation Testing

Mutation testing evaluates software tests by introducing controlled changes into a program and measuring whether the tests detect them.

mutation-testing
Mutex

A mutex is a synchronization primitive that allows only one thread or other execution unit at a time to access a protected resource.

mutex
Mutual exclusion

Mutual exclusion prevents concurrent activities from entering a protected critical section simultaneously, enabling coordinated access to shared resources.

mutual-exclusion
N-gram

An n-gram is a sequence of consecutive units used to represent local patterns and estimate probabilities in language and other sequential data.

n-gram
Naive Bayes classifier

A family of probabilistic classifiers that applies Bayes’ theorem using the assumption that features are conditionally independent given the class.

naive-bayes-classifier
Nathaniel Rochester

Nathaniel Rochester was an American computer engineer who helped design the IBM 701 and coauthored the proposal for the 1956 Dartmouth artificial intelligence research project.

nathaniel-rochester
Natural Language Processing

Natural language processing studies computational methods for analyzing, interpreting, and generating human language in text and speech.

natural-language-processing
Neighbor Discovery Protocol

Neighbor Discovery Protocol is an IPv6 control protocol for discovering local-link devices and routers, resolving link-layer addresses, and tracking neighbor reachability.

neighbor-discovery-protocol
Nested Cross-validation

Nested cross-validation separates model selection from performance estimation by placing an inner validation procedure inside an outer evaluation loop.

nested-cross-validation
Network Packet

A network packet is a formatted unit of data carried across a computer network, combining payload with information used for delivery and processing.

network-packet
Neural network inference

Neural network inference is the execution of a trained neural network to produce predictions or generated outputs from input data, usually without updating its parameters.

neural-network-inference
Neural Network Quantization

Neural network quantization represents model parameters and computations with reduced numerical precision to lower memory, bandwidth, and computational costs.

neural-network-quantization
Neural Radiance Field

A neural radiance field represents a three-dimensional scene as a learned function of position and viewing direction, enabling image synthesis from new viewpoints.

neural-radiance-field
Neural scaling law

An empirical relationship describing how neural-network performance changes with model size, training data, and computational resources.

neural-scaling-law
Neuro-symbolic Artificial Intelligence

Neuro-symbolic artificial intelligence integrates neural learning with explicit symbolic representations and reasoning to combine perceptual flexibility with structured inference.

neuro-symbolic-artificial-intelligence
Neuromorphic computing

Neuromorphic computing develops hardware and algorithms inspired by nervous systems, emphasizing distributed processing, local memory, temporal dynamics, and event-driven communication.

neuromorphic-computing
Nintendo Switch 2

Nintendo’s hybrid video game console, released in 2025 as the successor to the Nintendo Switch.

nintendo-switch-2
NIST Cybersecurity Framework

The NIST Cybersecurity Framework organizes cybersecurity risk management around shared outcomes, organizational profiles, and tiers describing the rigor of risk governance and management.

nist-cybersecurity-framework
Non-Maximum Suppression

Non-maximum suppression selects strong local responses or high-scoring detections while suppressing nearby or overlapping alternatives, reducing redundant outputs in computer vision.

non-maximum-suppression
Non-uniform memory access

Non-uniform memory access is a shared-memory architecture in which memory latency and bandwidth depend on the locations of processors and memory.

non-uniform-memory-access
Non-volatile memory

Non-volatile memory (NVM) retains stored information without continuous electrical power and includes technologies used for firmware, persistent storage, and specialized main memory.

nvm
Nonmonotonic Reasoning

Nonmonotonic reasoning allows conclusions drawn from incomplete information to be withdrawn when additional information becomes available.

nonmonotonic-reasoning
Normalized Discounted Cumulative Gain

Normalized discounted cumulative gain is a ranking metric that measures graded relevance while giving greater weight to items near the top of a result list.

normalized-discounted-cumulative-gain
Normalizing Flow

A normalizing flow models a probability distribution through invertible transformations, enabling both sampling and explicit density evaluation.

normalizing-flow
NoSQL

NoSQL denotes diverse database systems that use nonrelational data models, often emphasizing flexible representation, distributed operation, and workload-specific performance.

nosql
Not a Number

Not a Number (NaN) is a special floating-point value representing an undefined, invalid, or unrepresentable numerical result.

not-a-number
NP-completeness

NP-completeness identifies decision problems that have efficiently verifiable solutions and are at least as hard as every problem in NP.

np-completeness