Subcategories
All entries in Computer Science
Connectionist Temporal Classification trains sequence models from unaligned labels by summing the probabilities of all valid monotonic alignments.
connectionist-temporal-classificationConstitutional AIConstitutional AI trains language models to follow explicit principles through self-critique, revision, and AI-generated preference feedback.
constitutional-aiContent negotiationContent negotiation is an HTTP mechanism for selecting a representation of a resource according to client preferences, such as media type, language, or compression format.
content-negotiationContent-Addressable StorageContent-addressable storage identifies and retrieves data using identifiers derived from its contents, enabling deduplication, integrity verification, and immutable references.
content-addressable-storageContext WindowA context window is the bounded amount of tokenized information a language model can use during a generation request.
context-windowContinuation-passing styleContinuation-passing style is a programming style in which functions receive explicit continuations describing how their results should be used, making control flow explicit.
continuation-passing-styleContrastive LearningA representation-learning approach that learns similarities and distinctions by comparing related and unrelated examples.
contrastive-learningControl FlowControl flow is the ordering of computational steps, determined by sequencing, branching, repetition, calls, and other transfers of execution.
control-flowConvolutional neural networkA neural network architecture that uses shared, locally applied filters to learn patterns in images and other grid-structured data.
convolutional-neural-networkCoroutineA coroutine is a resumable computation that preserves execution state across suspension, supporting generators, cooperative multitasking, and asynchronous programming.
coroutineCPU cacheA CPU cache is a small, fast memory that reduces processor access time to frequently or recently used instructions and data.
cpu-cacheCPU SchedulingCPU scheduling allocates processor time among runnable tasks, balancing responsiveness, throughput, fairness, deadlines, and the costs of sharing computing hardware.
cpu-schedulingCRISP-DMCRISP-DM is an industry-neutral framework for planning and carrying out data-mining projects through six iterative phases, from business understanding to deployment.
crisp-dmCritical sectionA critical section is a region of code whose access to shared resources must be coordinated to prevent conflicting concurrent operations.
critical-sectionCross-attentionCross-attention lets one set of neural representations selectively retrieve information from another through learned query–key matching.
cross-attentionCryptanalysisCryptanalysis studies how to defeat cryptographic protections and evaluates the security of algorithms, protocols, and implementations under specified attack conditions.
cryptanalysisCryptographic Hash FunctionA cryptographic hash function produces a compact digest of data designed to resist inversion, collisions, and other adversarial manipulation.
cryptographic-hash-functionCryptographic nonceA cryptographic nonce is a value used to distinguish operations or protocol exchanges, with uniqueness or unpredictability requirements determined by its application.
cryptographic-nonceCryptographyCryptography studies mathematical methods for protecting information and enabling secure communication and computation in the presence of adversaries.
cryptographyCUDACUDA is a parallel computing platform and programming model developed by NVIDIA that enables general-purpose computing on its GPUs, and it dominates deep learning and scientific computing; CUDA 1.0 was released in 2007.
cudaCybersecurityCybersecurity protects digital systems, networks, and information through technical safeguards, organizational processes, and the management of security risks.
cybersecurityDamerau–Levenshtein DistanceDamerau–Levenshtein distance measures the minimum number of insertions, deletions, substitutions, and adjacent transpositions needed to transform one string into another.
damerau-levenshtein-distanceDario AmodeiAmerican artificial intelligence researcher and entrepreneur, co-founder and chief executive officer of Anthropic.
dario-amodeiData AugmentationData augmentation creates additional training examples through transformations or combinations of existing data, helping models learn useful invariances and generalize beyond their training samples.
data-augmentationData BackupData backup creates recoverable copies of digital information to protect against deletion, corruption, equipment failure, and other losses.
data-backupData BreachA data breach is a security incident involving unauthorized access to, disclosure of, or loss of control over protected information.
data-breachData CatalogA data catalog is a searchable inventory of data assets and their metadata, supporting discovery, interpretation, governance, and reuse.
data-catalogData CenterA facility that houses computing, storage, and networking equipment with the infrastructure needed for reliable digital services.
data-centerData compressionData compression encodes information using fewer bits, either preserving the original exactly or allowing controlled loss to reduce storage and transmission requirements.
data-compressionData Definition LanguageData Definition Language (DDL) is the part of a database language used to create, alter, and remove structures such as tables, schemas, and constraints.
data-definition-languageData EngineeringData engineering designs and operates the systems that collect, transform, store, and deliver reliable data for analytical and operational use.
data-engineeringData LakeA data lake stores diverse datasets at scale for reuse across analytics, machine learning, and other computational workloads.
data-lakeData lakehouseA data architecture that combines data-lake storage with transactional reliability, governance, and analytical capabilities associated with data warehouses.
data-lakehouseData Leakage (Machine Learning)Data leakage occurs when information unavailable under the intended prediction or evaluation conditions influences model development, making reported performance misleading.
data-leakageData LineageData lineage records the origins, transformations, and movement of data, enabling users to trace outputs to their sources and assess downstream dependencies.
data-lineageData ManagementData management coordinates the governance, organization, storage, integration, protection, use, and preservation of data throughout its life cycle.
data-managementData MartA data mart is a subject-focused analytical data collection designed to serve a particular business function, department, or group of users.
data-martData miningData mining uses computational and statistical methods to discover patterns, relationships, and predictive models in datasets.
data-miningData PortabilityData portability is the ability to transfer data between systems or services in a form that preserves its practical usability.
data-portabilityData processing unitA data processing unit is a programmable processor that offloads networking, storage, security, and infrastructure services from a server’s main CPU.
data-processing-unitData QualityData quality is the degree to which data accurately, reliably, and appropriately support their intended uses.
data-qualityData ReplicationData replication maintains copies of information across systems to improve availability, resilience, performance, and geographic access.
data-replicationData StructureA data structure organizes information and its relationships to support efficient access, modification, and processing in computer programs.
data-structureData VisualizationData visualization represents data graphically to support exploration, analysis, explanation, and communication.
data-visualizationData WarehouseA data warehouse integrates historical data from multiple sources into a governed environment optimized for analytical queries, reporting, and decision support.
data-warehouseDatabaseAn organized collection of data maintained for efficient access, modification, and controlled use, usually through a database management system.
databaseDatabase IndexA database index is an auxiliary access structure that accelerates data retrieval while imposing storage, maintenance, and consistency costs.
database-indexDatabase Management SystemA database management system is software that organizes, queries, protects, and maintains shared data while controlling access, consistency, concurrency, and recovery.
database-management-systemDatabase NormalizationDatabase normalization organizes relational schemas using dependencies and normal forms to reduce redundancy and prevent inconsistent updates.
database-normalizationDatabase ReplicationDatabase replication maintains coordinated copies of data across systems to improve availability, distribute workloads, and support recovery and data integration.
database-replicationDatabase SchemaA database schema defines the structure, relationships, and constraints of stored data, providing a framework for organizing, validating, and accessing information.
database-schemaDatabase ShardingDatabase sharding distributes a logical database across multiple independently managed partitions to increase storage capacity and processing throughput, while introducing challenges in routing, transactions, and operations.
database-shardingDatabase TransactionA database transaction groups operations into a controlled unit of work, providing guarantees about partial failure, concurrent execution, and the persistence of committed changes.
database-transactionDBSCANDBSCAN is a density-based clustering algorithm that identifies dense, connected groups of observations and labels points outside those groups as noise.
dbscanDe-identificationDe-identification reduces the association between data and identifiable individuals through technical transformations and controls, while retaining information useful for analysis or other purposes.
de-identificationDeadlockDeadlock is a state in which cooperating computations cannot progress because each awaits resources or events dependent on others in the same set.
deadlockDecision tree learningA supervised learning method that constructs branching rules from labeled examples to predict categories or numerical values.
decision-tree-learningDeclarative ProgrammingDeclarative programming expresses computations through relationships, rules, or desired results while delegating many execution decisions to an implementation.
declarative-programmingDeep Blue (chess computer)Deep Blue was an IBM chess-playing supercomputer that defeated reigning world champion Garry Kasparov in a six-game match in 1997.
deep-blueDeep LearningDeep learning is a branch of machine learning that learns layered representations of data, typically using neural networks with multiple processing layers.
deep-learning