3,135 articles
Differentially private stochastic gradient descent
Differentially private stochastic gradient descent (DP-SGD) is a training algorithm that clips each example's gradient and adds Gaussian noise, giving deep neural networks a formal differential privacy guarantee.
Diffractive neural network
A diffractive neural network, or diffractive deep neural network, performs machine learning inference through light passing through trained diffractive layers, introduced by UCLA researchers in 2018.
Diffusion map
Diffusion map is a nonlinear dimensionality reduction method introduced by Ronald Coifman and Stéphane Lafon in 2006 that embeds high-dimensional data by running a random walk on a similarity graph.
Diffusion maps
Diffusion maps are a nonlinear manifold learning method introduced by Ronald Coifman and Stéphane Lafon in 2006, in which a random walk on the data yields eigenfunction coordinates describing its geometry.
Diffusion model
A diffusion model, also called a diffusion probabilistic model, is a generative neural network that produces data by learning to reverse a gradual noising process step by step.
Diffusion sampling (machine learning)
Diffusion sampling is the iterative procedure a diffusion model uses to turn random noise into images, audio, or other data, applying a denoising network repeatedly.
DigiLocker
DigiLocker is India's government-operated digital document wallet, launched in 2015, where over 570 million users store official documents like driving licenses and marksheets with full legal validity.
Digital data
Digital data is information represented as sequences of binary digits that computers store, transmit, and process; its meaning depends on the encoding, since the same byte can represent different characters.
Digital filter
A digital filter is a system that computes an output from a sampled, discrete-time input signal using arithmetic, classified as FIR filters with fixed responses and IIR filters with feedback.
Digital image
A digital image is a picture represented as a finite array of pixels, each storing a quantized value of light intensity or color. The first was made in 1957.
Digital image processing
Digital image processing is the branch of signal processing that uses computers to enhance, transform, and analyze images, born in the early 1960s with NASA's Ranger 7 Moon pictures.
Digital Personal Data Protection Act, 2023
The Digital Personal Data Protection Act, 2023 (DPDP Act) is India's general statute for processing digital personal data, enacted in August 2023 and enforced by a Data Protection Board of India.
Digital quantum simulation
Digital quantum simulation (DQS) is a computational method that uses a programmable quantum computer to reproduce a quantum system's time evolution as a sequence of discrete quantum gates.
Digital signal processing
Digital signal processing (DSP) is the deliberate alteration of digital signals, by filtering, transforms, estimation, and related operations, to improve their quality, transmission, or storage.
Dijkstra's algorithm
Dijkstra's algorithm finds shortest paths from a source node to every other node in a graph with non-negative edge weights, conceived by Edsger W. Dijkstra in 1956.
DIKW pyramid
The DIKW pyramid, also called the knowledge hierarchy, is a model arranging data, information, knowledge, and wisdom in a rising sequence, each level built from the one below.
DimeNet
DimeNet, short for directional message passing neural network, is a graph neural network that predicts quantum-mechanical properties of molecules using both interatomic distances and angles.
Dimension (data warehouse)
A dimension, or data dimension, is a data warehouse table of descriptive attributes such as customer, product, or date, joined to a central fact table in a star schema.
Dimension table
Dimension table: in data warehousing, the table storing descriptive attributes (product, customer, date) that give context to numeric facts in a fact table; wide, few rows, surrogate-keyed, star schema component per Kimball.
Dimensional modeling
Dimensional modeling is a data warehouse design method organizing numeric measurements into fact tables surrounded by denormalized dimension tables, presented by Ralph Kimball and Kevin Strehlo in 1995.
Dimensionality reduction
Dimensionality reduction, also called dimension reduction, transforms high-dimensional data into fewer coordinates while minimizing information loss, through linear methods such as PCA and nonlinear manifold methods such as t-SNE and UMAP.
Dining philosophers problem
The dining philosophers problem is a classic concurrent programming example posed by Edsger W. Dijkstra in 1965, modeling shared resource allocation and illustrating deadlock and starvation.
Direction of arrival estimation
Direction of arrival (DOA) estimation determines the directions from which radio or acoustic signals arrive at a sensor array, underpinning radar, sonar, and wireless beamforming.
DisCoCat
DisCoCat, short for categorical compositional distributional semantics, is a mathematical model of meaning that combines word vectors with grammatical structure, introduced by Coecke, Sadrzadeh, and Clark in 2010.
Discogs
Discogs, short for discographies, is a user-built online database of music releases and a marketplace for buying and selling vinyl, CDs, and cassettes, founded in 2000.
Discontinuous deformation analysis
Discontinuous deformation analysis (DDA) is a numerical method that simulates the motion and deformation of discrete blocks in jointed rock masses, applied mainly to rockfall, rock slopes, and landslides.
Discounted cumulative gain
Discounted cumulative gain (DCG) is a ranking evaluation metric that discounts graded relevance by rank position, introduced by Järvelin and Kekäläinen in 2002 and widely used in information retrieval.
Discrete cosine transform
The discrete cosine transform (DCT), also called cosine transform, is a family of real-valued Fourier-related transforms, introduced in 1974, that underlies JPEG image and MP3 audio compression.
Discrete element method
The discrete element method (DEM), also called the discrete element model, is a numerical simulation technique that computes the motion of large particle assemblies contact by contact.
Discrete event simulation
Discrete event simulation is a modeling method where a system's state changes only at discrete event times, used to estimate waiting times, throughput, and bottlenecks.