3,135 articles
Adaptive Algorithms
Adaptive Algorithms: algorithms that modify their behavior when facing unseen tasks with limited training data (MeSH D000098426, 2025). Covers adaptive control, meta-learning, adaptive online learning, and adaptive versus non-adaptive performance comparisons.
Adaptive dynamic programming
Adaptive dynamic programming (ADP), also called approximate or neuro-dynamic programming, is a reinforcement learning method that approximates value functions to optimally control nonlinear systems forward in time.
Adaptive filter
An adaptive filter is a digital filter whose coefficients are adjusted automatically by an algorithm minimizing error, used for noise and echo cancellation, equalization, and system identification when the best response is unknown.
Adaptive filtering
Adaptive filtering is a signal processing method that recursively adjusts filter weights at each sample to minimize mean-square error, used in echo cancellation, equalization, and noise cancellation.
Adaptive histogram equalization
Adaptive histogram equalization (AHE) is an image processing technique that enhances local contrast by computing a separate histogram equalization for each small region of an image.
Adaptive large neighborhood search
Adaptive large neighborhood search, known as ALNS, is a metaheuristic for combinatorial optimization that repeatedly destroys and repairs parts of a solution, adjusting operators by performance.
Adaptive mesh refinement
Adaptive mesh refinement (AMR) is a numerical technique for solving partial differential equations, concentrating fine mesh cells where the solution needs them and saving memory and compute.
Adaptive particle swarm optimization
Adaptive particle swarm optimization (APSO) is a variant of particle swarm optimization that adjusts parameters like the inertia weight during the search instead of fixing them in advance.
Adaptive resonance theory
Adaptive resonance theory (ART) is a family of neural network models introduced by Stephen Grossberg in 1976 that learn new categories without forgetting old ones.
Additive white Gaussian noise
Additive white Gaussian noise (AWGN) is a signal-processing noise model with Gaussian amplitude and a flat power spectrum, used as the benchmark channel in communications engineering.
ADE20K
ADE20K is a densely annotated image dataset for scene parsing released by MIT's CSAIL, containing over 27,000 images labeled at the pixel level and spanning 365 scene types.
Adjacency list
An adjacency list, also called an adjacency-list representation or adjacency table, is a data structure for representing a graph where each vertex stores a list of its neighbors.
Adjacency matrix
An adjacency matrix, also called a connectivity matrix or sociomatrix, is a square matrix whose entries record the edges, or weights, between a graph's vertices.
Adversarial machine learning
Adversarial machine learning studies attacks on machine-learning systems and defenses against them. Its central defense, adversarial training, injects attack examples into training to produce robust classifiers.
AERMOD
AERMOD (American Meteorological Society/EPA Regulatory Model) is the US EPA's Gaussian plume air dispersion model, preferred for near-field regulatory use since 2005 and fully replacing ISC3 in 2006.
Affective computing
Affective computing is an interdisciplinary field combining psychology and computer science, founded by Rosalind Picard at MIT, whose 1997 book argued that natural interaction with computers requires machines to recognize, understand, and express emotion.
Affinity analysis
Affinity analysis is a data mining method that finds items occurring together, such as products bought in the same basket, and expresses them as association rules.
Affinity propagation
Affinity propagation is a clustering algorithm, introduced by Frey and Dueck in 2007, that exchanges messages between data points to find exemplars without a preset cluster count.
Agentic data platform
Agentic data platform: enterprise data infrastructure (also agentic data cloud, agentic data management) rebuilt so AI agents can ingest, analyze, and act on governed data; spans Google BigQuery agents, Databricks Genie, Snowflake Intelligence, governance frameworks, and benchmarks like Spider 2.0.
Agglomerative hierarchical clustering
Agglomerative hierarchical clustering is a bottom-up clustering method that starts with each data point as its own cluster and merges the closest pairs, yielding a dendrogram.
Agile Data Warehouse Design
Agile Data Warehouse Design: agile approach to dimensional data warehouse modeling via BEAM (Business Event Analysis and Modeling), the 7Ws, and modelstorming, from the 2011 Corr and Stagnitto book.
Aho–Corasick algorithm
The Aho–Corasick algorithm is a string-searching algorithm that locates all occurrences of a set of keywords in a text in a single pass, published by Alfred V. Aho and Margaret J. Corasick in 1975.
AI Act (Brazil)
The AI Act of Brazil, formally Bill No. 2338 of 2023, is a pending bill that would set national risk-based rules for governing artificial intelligence systems.
AI alignment
AI alignment, also called the AI control problem, is the research field of making AI systems pursue their designers' intended goals rather than misaligned ones. It uses techniques like RLHF.
AI and Data Act (Canada)
The Artificial Intelligence and Data Act (AIDA) was a proposed Canadian statute requiring risk mitigation for high-impact AI systems; it died on the order paper in January 2025.
AI anthropomorphism
AI anthropomorphism, or artificial intelligence anthropomorphism, is the attribution of humanlike characteristics, such as emotions, identity, and personality, to AI systems, from ELIZA's 1966 users to modern chatbots.
AI Campus (Germany)
AI Campus (KI-Campus) is a free German online learning platform for artificial intelligence, operated by the Stifterverband and offering courses, videos, and podcasts in German and English.
AI codes of conduct and model-release policies
Voluntary AI codes of conduct and model-release policies are commitments by AI developers to evaluate models against capability thresholds and apply stricter safeguards, without being compelled by statute.
AI containment
AI containment, also called capability control, is the set of technical measures restricting what an AI system can do, using sandboxes, egress controls, and human-in-the-loop gates, distinct from alignment.
AI Feynman
AI Feynman is a physics-inspired symbolic regression algorithm that discovers equations from data using neural networks, developed by Silviu-Marian Udrescu and Max Tegmark at MIT and published in 2020.