3,135 articles
Reduced-order modeling
Reduced-order modeling (ROM) builds low-dimensional surrogates of high-dimensional simulations of complex systems, running orders of magnitude faster than the full-order model while retaining most of its accuracy, most commonly by POD-Galerkin projection.
Reference data management
Reference data management governs the code lists (ISO 3166 country codes, ISO 4217 currencies, NACE, LEI) that constrain other data; a subset of master data requiring versioning, ownership, and controlled change.
Referential integrity
Referential integrity is a database property requiring that every foreign key value matches a referenced key or is null, enforced in SQL by foreign key constraints.
Reformer (transformer model)
Reformer is an efficient Transformer architecture introduced in January 2020 by Kitaev, Kaiser, and Levskaya, using LSH attention and reversible layers to process very long sequences.
RefSeq
RefSeq, short for Reference Sequence, is a database maintained by the US National Center for Biotechnology Information that provides curated, non-redundant reference sequences of genomic DNA, transcripts, and proteins for diverse organisms.
Region growing
Region growing, also known as the region growing algorithm, is an image segmentation method that grows connected regions from seed points by adding similar neighboring pixels.
Region proposal network
A region proposal network (RPN) is a fully convolutional module that scans a shared image feature map and predicts candidate object regions, introduced in Faster R-CNN in 2015.
Regret bound
A regret bound is a theorem in online learning limiting how much worse an algorithm's cumulative loss can be than the best fixed strategy chosen in hindsight.
Regret matching
Regret matching is an adaptive rule for choosing actions in repeatedly played games, introduced by Hart and Mas-Colell in 2000, whose play converges to correlated equilibria.
Regulation of algorithms
Regulation of algorithms is the set of laws, standards, and enforcement mechanisms authorities apply to algorithmic and AI systems, exemplified by the EU AI Act, effective from 2024.
Regulation of artificial intelligence
Regulation of artificial intelligence, or AI regulation, is the body of laws governments apply to AI systems, led by the EU's risk-based AI Act, in force since 2024.
Relation extraction
Relation extraction is the natural language processing task of identifying semantic relationships between entities in text, outputting structured triples that feed knowledge graphs and question answering.
Relational algebra
Relational algebra is a procedural query language for the relational model of databases, introduced by IBM researcher Edgar F. Codd in his 1970 paper on relational data.
Relational database
A relational database stores data in tables of rows and columns and follows the relational model proposed by E. F. Codd in 1970, queried with SQL.
Relational model
The relational model, also called the relational data model, organizes database data into tables called relations, and was proposed by E. F. Codd at IBM in 1970.
RelationalAI
RelationalAI is an American software company, founded in 2017 and based in Berkeley, California, whose decision intelligence platform runs a relational knowledge graph inside Snowflake.
Relative pose estimation
Relative pose estimation is a computer vision method that determines the rotation and translation direction of one camera relative to another from point correspondences between two images.
Relevance feedback
Relevance feedback is an information retrieval technique in which a search system reformulates a user's query based on documents marked relevant or nonrelevant, introduced by Rocchio in 1971.
Relevance vector machine
The relevance vector machine (RVM) is a Bayesian kernel method for regression and classification introduced by Michael E. Tipping in 1999, typically far sparser than the support vector machine.
Reliability of Wikipedia
The reliability of Wikipedia, also called the accuracy of Wikipedia, is how accurate its volunteer-edited content is, as measured by external audits like Nature's 2005 comparison with Britannica.
Remark Holdings
Remark Holdings, Inc. is a technology company based in Las Vegas, Nevada, offering AI-powered analytics, computer vision, and smart agent solutions; delisted from Nasdaq in 2024.
Rényi differential privacy
Rényi differential privacy is a relaxation of differential privacy proposed by Ilya Mironov in 2017 that bounds the Rényi divergence between outputs on neighboring datasets.
Repetition code
The repetition code is a quantum error-correcting code that encodes one logical qubit into n entangled physical qubits, correcting bit-flip errors by majority vote but not phase errors.
ResearchGate
ResearchGate is a Berlin-based academic social networking site where researchers share publications, ask and answer research questions, and track metrics, founded in 2008 by physicians Ijad Madisch and Sören Hofmayer.
Reservoir computing
Reservoir computing, also known as physical reservoir computing, is a machine learning framework where a fixed reservoir processes temporal data and only a linear readout is trained.
Reservoir computing forecasting of chaotic systems
Reservoir computing forecasting of chaotic systems uses reservoir computing, a machine learning framework with a fixed recurrent network and trained readout, to predict chaotic dynamics.
Residual dense network
A residual dense network (RDN) is a convolutional neural network architecture for image restoration, introduced by Yulun Zhang and colleagues at CVPR 2018 for super-resolution, denoising, and deblurring.
Residual learning
Residual learning is a neural network training approach where each block learns a correction added to its input through a shortcut, enabling 152-layer networks that won ILSVRC 2015.
Residual neural network
A residual neural network (ResNet) is a deep neural network whose layers learn residual functions via identity shortcuts, introduced by Kaiming He's team at Microsoft Research and winning ILSVRC 2015.
Residual reinforcement learning
Residual reinforcement learning is a robot-control method in which a learned policy adds corrections to a fixed base controller, keeping its reliability while learning fixes its weaknesses.