aiwiki.page
English
Home / Category

Computer Science

1034 entriesPage 5 of 18

Subcategories

All entries in Computer Science

Deep Q-Network

A deep Q-network is a reinforcement-learning method that uses a deep neural network, experience replay, and a target network to estimate action values and learn decisions from experience.

deep-q-network
DeepLab

DeepLab is a family of convolutional neural network models for semantic image segmentation, known for atrous convolution, multiscale context aggregation, and encoder–decoder refinement.

deeplab
DeepMind

DeepMind is an artificial intelligence research organization known for reinforcement learning, game-playing systems, AlphaFold, and its integration into Google DeepMind.

deepmind
DeepSeek

DeepSeek is a Chinese artificial intelligence company based in Hangzhou, known for releasing large language models with open weights, especially the reasoning model R1.

deepseek
DeepSeek 4.1

DeepSeek 4.1 is a generation of multimodal artificial intelligence models, introduced with DeepSeek-V4.1-Flash in September 2026.

deepseek-4-1
DeepSeek 4.1 Flash

DeepSeek 4.1 Flash (DeepSeek-V4.1-Flash) is a multimodal Mixture-of-Experts language model released in September 2026, with a 552-billion-parameter backbone and a one-million-token context window.

deepseek-4-1-flash
DeepSeek-R1

DeepSeek-R1 is an open-weight language-model family developed to improve reasoning through reinforcement learning and distillation.

deepseek-r1
DeepWiki

DeepWiki is an AI-powered service from Cognition that generates navigable documentation and answers questions about software repositories.

deepwiki
Defense in Depth

Defense in depth is a security strategy that combines multiple complementary safeguards so that the failure or bypass of one does not defeat the entire system.

defense-in-depth
Dell Technologies

Dell Technologies is an American technology company producing personal computers, servers, storage systems, and related enterprise services.

dell-technologies
Denial-of-Service Attack

A denial-of-service attack deliberately impairs a system’s availability by exhausting resources, exploiting failures, or obstructing legitimate access.

denial-of-service-attack
Deno

Deno is an open-source JavaScript and TypeScript runtime combining restricted system access, web-standard APIs, integrated development tools, and Node.js compatibility.

deno
Denoising diffusion implicit model

A denoising diffusion implicit model is a diffusion-based generative method that enables deterministic or stochastic sampling, often with far fewer steps than the original diffusion process.

denoising-diffusion-implicit-model
Denormalization

Denormalization deliberately introduces redundant or precomputed data into a database design to simplify queries or improve read performance, at the cost of additional storage and maintenance.

denormalization
Dense retrieval

Dense retrieval ranks documents or other items by comparing learned vector representations of queries and candidates, enabling search beyond exact term overlap.

dense-retrieval
Depth-first Search

Depth-first search traverses a graph or tree by exploring each branch as far as possible before backtracking to explore alternatives.

depth-first-search
DETR

DETR is a Transformer-based object detector that predicts objects as an unordered set, using bipartite matching to train without hand-designed anchors or non-maximum suppression.

detr
Device Driver

A device driver is software that enables an operating system or another software environment to control and communicate with a hardware or virtual device.

device-driver
Differential Privacy

Differential privacy is a mathematical framework for limiting how much an analysis can reveal about any one individual’s data.

differential-privacy
Diffusion model

A generative machine-learning model that learns to produce data by reversing a gradual noise-corruption process.

diffusion-model
Digital preservation

Digital preservation is the managed maintenance of digital information so that it remains authentic, understandable, and usable over time.

digital-preservation
Digital Signature

A digital signature is a cryptographic mechanism for verifying the origin and integrity of data using a private signing key and a corresponding public verification key.

digital-signature
Dijkstra's Algorithm

Dijkstra’s algorithm computes shortest paths in graphs with nonnegative edge weights by repeatedly finalizing the nearest unsettled vertex.

dijkstra-algorithm
Diode

A diode is a two-terminal electronic device whose nonlinear electrical behavior enables rectification, switching, voltage control, light emission, and photodetection.

diode
Direct Preference Optimization

Direct Preference Optimization trains generative models on ranked responses using a classification-style objective derived from regularized reward maximization.

direct-preference-optimization
Disaster Recovery

Disaster recovery restores information systems, data, and technology-dependent services after major disruptions through coordinated technical and organizational measures.

disaster-recovery
DistilBERT

DistilBERT is a compact Transformer language model trained by knowledge distillation to retain much of BERT’s performance with fewer parameters and faster inference.

distilbert
Distributed Computing

Distributed computing coordinates networked computers to perform computation, manage shared data, and provide services despite communication delays and component failures.

distributed-computing
Distributed Consensus

Distributed consensus enables independent computing processes to agree on a common decision despite failures, communication delays, or malicious behavior.

distributed-consensus
Distribution Shift

Distribution shift is a difference between the data distributions used to develop a predictive model and those encountered during evaluation or deployment.

distribution-shift
Divide and Conquer

An algorithm-design paradigm that solves a problem by decomposing it into smaller problems and combining their solutions.

divide-and-conquer
DNA data storage

DNA data storage encodes digital information in nucleotide sequences, combining high potential density and long-term stability with substantial writing, reading, and access constraints.

dna-data-storage
DNP3

DNP3 is a communications protocol for monitoring and controlling industrial equipment, particularly in electric utilities, with standardized data objects, event reporting, and remote-control functions.

dnp3
DNS wildcard

A DNS wildcard supplies records for otherwise nonexistent domain names using a specially named record source and rules based on the DNS name hierarchy.

dns-wildcard
Docstring

A docstring is a string embedded in source code that documents a program element and can often be retrieved by development tools or at runtime.

docstring
Domain Adaptation

Domain adaptation is a machine-learning approach that transfers predictive knowledge between related data distributions to improve performance in a target domain.

domain-adaptation
Domain name registry

A domain name registry maintains registration records and delegation data for an Internet domain, usually a top-level domain, and operates the systems through which names are registered.

domain-name-registry
Domain Name System

The hierarchical, distributed naming system that associates Internet domain names with addresses and other resource data.

domain-name-system
Dongchedi

Dongchedi, also known as DCar, is a Chinese automotive information, community, and vehicle-trading platform launched in 2017.

dongchedi
Doubao, Hongguo, and Consumer Demand for AI

Comparisons between Doubao and Hongguo illuminate differences in entertainment demand, AI adoption, audience measurement, and the economics of consumer applications.

doubao
Double Descent

Double descent is a pattern in which predictive error decreases, rises near an interpolation threshold, and decreases again as model capacity or training increases.

double-descent
Dropout (neural networks)

Dropout is a neural-network regularization technique that randomly suppresses activations during training to reduce overfitting.

dropout
DuckDB

DuckDB is an open-source, in-process, column-oriented analytical database management system written in C++ and released under the MIT License.

duckdb
Dynamic Array

A dynamic array is a resizable sequence that combines constant-time indexed access with efficient amortized insertion at its end.

dynamic-array
Dynamic programming

A mathematical and computational method that solves structured problems by combining and reusing solutions to subproblems.

dynamic-programming
Early Stopping

Early stopping limits iterative model training by selecting a stopping point, often using validation performance, to control overfitting and computational cost.

early-stopping
eBPF

eBPF is a verified execution framework that enables event-driven programs to extend operating-system behavior, particularly for networking, observability, and security.

ebpf
ECMAScript Modules

ECMAScript modules are JavaScript’s standardized system for declaring dependencies, sharing live bindings, and organizing code across browsers, servers, and development tools.

ecmascript-modules
Edit Distance

Edit distance measures the minimum cost of transforming one sequence into another using specified operations, such as insertions, deletions, and substitutions.

edit-distance
Electron-Beam Lithography

Electron-beam lithography uses a controlled beam of electrons to pattern radiation-sensitive materials, enabling nanoscale fabrication and the production of masks for semiconductor manufacturing.

electron-beam-lithography
Electronic Data Interchange

Electronic data interchange automates the exchange of standardized business documents between organizations’ information systems.

electronic-data-interchange
Electronic Design Automation

Electronic design automation comprises software methods and tools for designing, verifying, and preparing electronic circuits and systems for manufacture.

electronic-design-automation
Email

Email is a store-and-forward system for sending messages electronically between users and servers, built on open standards since the 1980s.

email
Emergent abilities

Emergent abilities are model capabilities that appear abruptly with changes in scale or training, although their interpretation depends strongly on measurement and evaluation.

emergent-abilities
Empirical risk minimization

Empirical risk minimization selects a predictive model by minimizing its average loss on observed data, using that loss as a proxy for population risk.

empirical-risk-minimization
Emulation

Emulation reproduces another computing system’s behavior, enabling software compatibility, hardware development, testing, and digital preservation.

emulation
Encoder–decoder architecture

A neural-network design in which an encoder represents input data and a decoder uses that representation to produce an output.

encoder-decoder-architecture
Encryption

Encryption transforms data with a key so that only authorized parties can recover its meaning, and it underpins modern digital security.

encryption
Endgame tablebase

An endgame tablebase stores exhaustively computed results for game positions with limited material, enabling exact evaluation and optimal play under specified rules.

endgame-tablebase
Endpoint Detection and Response

Endpoint detection and response continuously records device activity to identify intrusions, support investigations, and contain security incidents.

endpoint-detection-and-response