Distant supervision - Distant supervision creates training signals by connecting unlabeled examples with an external source of information, rather than manually labeling every...
Distillation - Distillation is training a student model using information supplied by a teacher model or ensemble.
Distributed algorithm - A distributed algorithm is a procedure carried out by multiple computing participants that perform local work and coordinate through communication.
Distributed algorithmic mechanism design - Distributed algorithmic mechanism design studies how to design computationally practical rules for networked participants whose incentives may differ, when...
Distributed cache - A distributed cache is a caching system used across networked computers, commonly providing a shared cache service and often distributing cached items over...
Distributed computing - Distributed computing is the use of multiple networked computers or processes to perform a coordinated task or provide a service.
Distributed concurrency control - Distributed concurrency control coordinates overlapping operations or transactions on data managed across multiple networked nodes.
Distributed constraint optimization - Distributed constraint optimization coordinates decisions controlled by different agents so that their combined assignment optimizes a shared objective...
Distributed constraint satisfaction - Distributed constraint satisfaction is a way of solving a constraint problem in which variables, constraints, or decision responsibilities are distributed...
Distributed data store - A distributed data store is a system that stores and retrieves data across multiple networked machines.
Distributed database - A distributed database is a database whose data and database operations are managed across multiple networked nodes.
Distributed file system for cloud - A distributed file system for cloud is a file-storage system that uses multiple networked machines to provide file access for cloud or cloud-scale workloads.
Distributed ledger - A distributed ledger is a shared record maintained across multiple networked participants or nodes, using agreed rules to validate and incorporate changes.
Distributed memory - Distributed memory is a computer architecture or programming model in which processing units work with separate local memories and communicate to exchange...
Distributed representation - A distributed representation encodes an item through a pattern across several representational units, with individual units participating in the...
Distributed source coding - Distributed source coding compresses statistically related sources using separate encoders and reconstructs them at a decoder that can use their relationship.
Distributed transaction - A distributed transaction is a transaction whose work involves more than one networked resource or database participant.
Distributed tree search - Distributed tree search divides the exploration of a search tree among cooperating processors or workers.
Distribution - A distribution describes how values of a variable are spread across possible outcomes or ranges.
Distributional - relational database - A distributional - relational database is a database approach that combines structured relations with distributional representations of meaning.
Distributional robustness - Distributional robustness is the ability of a model or decision rule to maintain acceptable performance when the data distribution differs from the one used...
Distributional semantics - Distributional semantics is an approach to representing meaning through patterns of language use, especially the contexts in which words or other...
Distributional similarity - Distributional similarity is similarity inferred from how linguistic items occur across contexts in a body of text.
Distributional Soft Actor Critic - Distributional Soft Actor Critic, or DSAC, is a family of off-policy reinforcement-learning methods for continuous control that combines maximum-entropy...
Distributionally robust optimization - Distributionally robust optimization (DRO) chooses a model or decision by minimizing its worst expected loss across a specified set of possible probability...
Distributionfree tests - Distribution-free tests are statistical tests whose null reference distribution does not depend on the precise form of the population distribution within a...
Divergence - In vector calculus, divergence measures the local net outward flow of a vector field per unit volume, or per unit area in two dimensions.
Divergence-from-randomness model - A divergence-from-randomness model is an information-retrieval model that weights query terms according to how their occurrence in a document departs from a...
Divide-and-conquer algorithm - A divide-and-conquer algorithm solves a problem by splitting it into smaller instances, solving those instances, and combining their answers.
Division model (Fitzgibbon) - The division model associated with Fitzgibbon is a compact mathematical model of radial lens distortion.
Divisive clustering - Divisive clustering is a top-down approach to grouping data: start with everything in one cluster and repeatedly split the least coherent group until each...
Divisive Communities - Divisive communities are groups identified by progressively splitting a graph into smaller parts.
Dixon's Q test - Dixon's Q test is an outlier test based on ratios of gaps between ordered observations.
DMAIC - DMAIC stands for Define, Measure, Analyze, Improve and Control.
DOACROSS parallelism - DOACROSS parallelism executes work from different loop iterations concurrently while preserving required dependencies between those iterations.
Document-at-a-time - Document-at-a-time is a search-query evaluation strategy that combines the contributions of query terms for one document before moving to another document.
Document classification - Document classification assigns one or more category labels to a document based on its content or other relevant information.
Document clustering - Document clustering is the process of grouping documents according to patterns of similarity in their representations.
Document-oriented database - A document-oriented database stores and queries records as structured documents, commonly containing named fields, nested objects and arrays.
Document partitioning - Document partitioning divides a search collection into subsets of documents and maintains a local index for each subset.
Document retrieval - Document retrieval is the process of finding documents that are relevant to a user's information need within a collection.
Document-rotation denoising - Document-rotation denoising is a language-model pretraining task in which a document is cyclically shifted to start at a randomly chosen token, and the...
Document structuring - Document structuring is the natural-language-generation task of organizing selected information into a coherent document.
Document-term matrix - A document-term matrix is a numerical table representing documents through selected text features.
DOE mean plot - A DOE mean plot shows the average response at each level of factors in a designed experiment. DOE stands for design of experiments.
Domain - A domain is the area, setting, or set of inputs to which a model, task, or body of knowledge applies. The precise meaning depends on context.
Domain adaptation - Domain adaptation adjusts a machine-learning system so that knowledge learned from one data setting can be useful in another.
Domain closure - Domain closure is an assumption that every object in a modeled domain is accounted for by the specified names or ground terms.