3,135 articles
Augmented analytics
Augmented analytics: AI, machine learning, and NLP applied to data preparation, insight generation, and explanation in BI platforms. Coined by Gartner in 2017; distinct from augmented intelligence and from full automation of decisions.
Augmented Lagrangian method
The augmented Lagrangian method (ALM), originally called the method of multipliers, is a constrained optimization algorithm combining the Lagrangian with a quadratic penalty term and Lagrange multiplier estimates.
Authorization
Authorization, often abbreviated AuthZ, is the process of deciding whether a user, program, or process is permitted to perform an action on a resource, granted only after authentication establishes identity.
Autoencoder
An autoencoder, also called an autoassociator, is a neural network trained to reconstruct its own input, learning compressed codes used for dimensionality reduction and anomaly detection.
Automata learning
Automata learning is a machine learning technique that infers formal state-machine models, such as DFAs and Mealy machines, by actively querying a system, used for verification and testing.
Automatic image annotation
Automatic image annotation is a machine learning method that assigns descriptive keywords to digital images without human effort, studied alongside tag refinement and tag-based image retrieval.
Automatic number-plate recognition
Automatic number-plate recognition, also called automatic license plate recognition (ALPR), is a surveillance technology that uses cameras and optical character recognition to read vehicle plates, invented in 1976 in the United Kingdom.
Automatic summarization
Automatic summarization is a natural language processing method that condenses documents by selecting key sentences or generating new text, beginning with Luhn's 1958 auto-abstract and now dominated by large language models.
Automatic target recognition
Automatic target recognition (ATR) is a processing task that detects and classifies targets from sensor signatures, originally military and now applied to ship detection and sea-ice monitoring.
Autoregressive neural network
An autoregressive neural network is a neural network that predicts the next value of a sequence from its own previous values, spanning forecasting and generative models like WaveNet.
Auxiliary learning
Auxiliary learning is a machine learning approach in which a model trains on auxiliary tasks alongside the primary task, using the parallel objectives to improve feature learning and generalization.
Average-case complexity
Average-case complexity is the branch of complexity theory that measures an algorithm's resource needs on typical inputs drawn from a probability distribution, introduced by Leonid Levin in 1984.
AVL tree
The AVL tree, or Adelson-Velskii Landis tree, is a self-balancing binary search tree, invented in 1962, in which search, insertion, and deletion take O(log n) time.
AWS Database Migration Service
AWS Database Migration Service (AWS DMS) is Amazon Web Services' managed service for migrating and continuously replicating databases such as Oracle, MySQL, PostgreSQL, and SQL Server into AWS, launched in 2016.
AWS Lake Formation
AWS Lake Formation: Amazon's fully managed data lake governance service, GA August 2019, using Glue Data Catalog grants, LF-Tags, and cross-account RAM sharing for column, row, and cell-level access control.
Azkaban
Azkaban is an open-source Java batch workflow job scheduler created at LinkedIn for Hadoop jobs, using .job files, MySQL plus web and executor servers, cron scheduling, and Kubernetes containerization in 4.0.0.
Azure Event Hubs
Azure Event Hubs is Microsoft's fully managed, real-time event streaming platform (PaaS), ingesting millions of events per second via Kafka, AMQP 1.0, and HTTPS. Distinguished by partitioned logs, consumer groups, throughput-unit scaling, and a Kafka-compatible endpoint requiring no code changes; generally available since October 2014.
Azure Machine Learning
Azure Machine Learning is Microsoft's managed cloud platform for the ML lifecycle: training, deployment, MLOps, AutoML, a feature store, and online and batch endpoints, launched in 2015 and rebuilt as Azure ML service (preview 2017, GA 2018) with v2 SDKs replacing retiring v1.
Azure Synapse Analytics
Azure Synapse Analytics is Microsoft's unified cloud analytics platform, formerly Azure SQL Data Warehouse, announced November 4, 2019. It combines dedicated and serverless SQL pools, Apache Spark, and Data Factory-style pipelines, with Microsoft now steering new customers to Fabric.
B-tree
A B-tree is a balanced, multiway search tree in which nodes hold many keys and children, invented by Bayer and McCreight at Boeing in 1970 and standard in database indexes.
B+ tree
A B+ tree, also written B plus tree, is a balanced tree data structure that keeps all records in linked leaf pages, serving as the standard database index.
Backdoor detection (machine learning)
Backdoor detection is a set of security techniques for determining whether a trained neural network carries a hidden trigger that forces attacker-chosen labels, by offline scanning or run-time analysis.
Backfill
Backfill (data engineering): rerunning a pipeline over historical data to populate new tables, fix bugs, or apply changed logic; requires idempotency, controlled ordering, throttling, and reconciliation.
Background subtraction
Background subtraction is a computer vision technique for stationary cameras that compares each video frame with a statistical background model to produce a foreground mask.
Backlink
A backlink, also called an inbound link, is a hyperlink on one website pointing to a page on a different website, treated as an endorsement.
Backpropagation
Backpropagation, also known as backprop, is the standard algorithm for training neural networks, computing gradients of a loss function with respect to every weight using the chain rule.
Backpropagation neural network
A backpropagation neural network is a feedforward neural network trained by backpropagation, which repeatedly adjusts weights to minimize the difference between actual and desired outputs.
Backpropagation through time
Backpropagation through time (BPTT) is the algorithm used to compute gradients in recurrent neural networks by unfolding the recurrence over time steps and applying ordinary backpropagation, as formalized by Paul Werbos in 1990.
Backtracking
Backtracking, or backtracking search, is a class of algorithms for solving constraint satisfaction problems, formalized by Golomb and Baumert in 1965 and famously applied to the eight queens puzzle.
Backward chaining
Backward chaining is a goal-driven inference method that starts from a hypothesis and works backward through rules to find supporting facts; it underlies Prolog and expert systems.