3,135 articles
Artificial intelligence in medicine
Artificial intelligence in medicine (AIM, medical AI): applying AI and machine learning to diagnosis, imaging, decision support, and drug discovery. Began in the 1970s with Dendral-era symbolic systems; today dominated by FDA-cleared radiology tools and large language models.
Artificial neuron
An artificial neuron, first modeled as the 1943 McCulloch–Pitts neuron, is a mathematical function computing weighted inputs with a bias and an activation, the basic unit of artificial neural networks.
ARX model
The ARX model (autoregressive with exogenous input) predicts a system's output from its own past values and past values of an external input, estimated by linear least squares.
ArXiv
ArXiv (pronounced "archive") is an open-access repository of preprints in physics, mathematics, computer science, and related fields, created by physicist Paul Ginsparg at Los Alamos in 1991.
Ascend.io
Ascend.io, also written Ascend (legal name Ascension Labs), is a Palo Alto company founded in 2015 by Sean Knapp selling the Agentic Data Engineering platform with the Otto AI agent, pushdown execution on BigQuery, Databricks, and Snowflake, and $50M raised to Series B.
Ash (Alien)
Ash, or Science Officer Ash, is a fictional android played by Ian Holm in the 1979 science-fiction horror film Alien, the science officer of the commercial towing vessel Nostromo.
Ashley Madison data breach
The Ashley Madison data breach, also called the Ashley Madison hack or leak, exposed details of about 36 million users of the infidelity dating site in 2015.
Aspect-based sentiment analysis
Aspect-based sentiment analysis (ABSA) is a natural language processing method that identifies sentiment toward specific aspects of an entity, such as a laptop's screen or keyboard, in text.
Assignment problem
The assignment problem, also called the linear assignment problem, is a combinatorial optimization problem: assign n workers to n jobs one-to-one at least total cost.
ASSISTments
ASSISTments is a free, web-based math tutoring platform created in 2003 at Worcester Polytechnic Institute by Neil and Cristina Heffernan, with randomized-trial evidence of improving achievement.
Association for the Advancement of Artificial Intelligence
The Association for the Advancement of Artificial Intelligence (AAAI), founded in 1979, is a nonprofit scientific society that runs the annual AAAI Conference on Artificial Intelligence.
Association rule learning
Association rule learning, also called association rule mining, is a data mining method that finds if-then relationships between items in large transaction databases, used in market basket analysis.
Associative array
An associative array is an abstract data type storing key–value pairs, also called a map, dictionary, or hash, where each key maps to at most one value.
AstroNet
AstroNet is a deep convolutional neural network by Christopher Shallue and Andrew Vanderburg that classifies Kepler light-curve signals as planets or false positives, discovering Kepler-90i and Kepler-80g.
AsyncAPI
AsyncAPI is an open-source, protocol-agnostic specification under the Linux Foundation for describing event-driven and message-driven APIs; created in 2016 by Fran Méndez, sister to OpenAPI, latest version 3.1.0.
Asynchronous stochastic gradient descent
Asynchronous stochastic gradient descent, or Async SGD, is a distributed training scheme where workers update a shared model without waiting for each other, trading synchronization for stale gradients.
At-least-once delivery
At-least-once delivery: a messaging guarantee that every message is delivered one or more times, never lost but possibly duplicated; implemented via acks and retries, with duplicates handled by idempotent consumers, as in Kafka and EventMesh.
Ataccama
Ataccama (Ataccama ONE) is a data management software company founded in 2007 as an Adastra spin-off, headquartered in Boston and Toronto, known for its unified data quality, governance, and agentic AI platform.
Atlan
Atlan (Atlan Pte. Ltd., founded 2019, San Francisco) is an enterprise data catalog and metadata platform marketed as the context layer for AI, with 80+ connectors, lineage, governance, an MCP server, a $750M valuation, and $105M Series C funding led by GIC.
Atom search optimization
Atom search optimization (ASO) is a physics-inspired metaheuristic introduced in 2018 that finds global optima by simulating atoms moving under Lennard-Jones interaction and constraint forces in a solution space.
Atomic decomposition
Atomic decomposition is a signal processing method that represents a signal as a sparse linear combination of elementary waveforms, called atoms, drawn from a redundant dictionary.
Atomicity (database systems)
Atomicity, also called an atomic transaction, is the database property that a transaction either completes entirely or not at all; it is the A in the ACID properties.
AtomNet
AtomNet is a deep convolutional neural network that predicts the bioactivity of small molecules bound to protein targets, introduced in 2015 by Atomwise in San Francisco.
Attention distillation
Attention distillation is a knowledge distillation method that trains a smaller student model to reproduce the attention maps of a larger teacher, typically a Transformer.
AttentiveFP
AttentiveFP is a graph neural network for molecular property prediction that applies attention at the atom and molecule levels, introduced by Xiong et al. in 2020.
Attractor network
An attractor network, or attractor neural network, is a recurrent neural network whose dynamics settle into stable activity patterns called attractors, used to model memory and decision-making.
Attribute reduction (rough set theory)
Attribute reduction is a feature selection method from rough set theory that finds a minimal attribute subset, called a reduct, preserving the classification ability of the full attribute set.
Attribute-based access control
Attribute-based access control (ABAC), also called policy-based access control, is an access control model that grants access by evaluating attributes of the subject, object, and environment against policy rules.
Audio deepfake detection
Audio deepfake detection is a machine learning task that decides whether speech is genuine or synthetically generated, used in call center fraud screening, forensics, and disinformation analysis.
Audio source separation
Audio source separation, often called the cocktail-party problem, uses signal processing and machine learning to isolate individual voices or instruments from a mixed recording, serving speech enhancement, music demixing, and ASR front ends.