3,135 articles
DrugBank
DrugBank is a curated online database combining drug chemistry and clinical data with protein targets, interactions, and mechanisms, first released in 2006 by the University of Alberta.
Dual branch network
A dual branch network is a neural network architecture with two parallel pathways whose outputs are combined by a fusion step, in Siamese or independent-branch form.
Dual decomposition
Dual decomposition is an optimization method that solves a large constrained problem by splitting it into subproblems coordinated through dual variables acting as prices, allowing parallel solution.
Dual learning
Dual learning is a machine learning framework that jointly trains two related tasks, such as translating between two languages, so each improves the other from unlabeled data.
Dual-tree complex wavelet transform
The dual-tree complex wavelet transform (DTCWT), introduced by N.G. Kingsbury in 1998, runs two real wavelet transforms in parallel, giving near shift invariance and six directional subbands in 2-D.
Duality (optimization)
Duality in optimization, notably Lagrangian duality, pairs a primal minimization problem with a dual maximization problem whose value bounds the primal and usually equals it for convex problems.
DuckDB
DuckDB is an open-source, in-process analytical (OLAP) SQL database system created by Mark Raasveldt and Hannes Mühleisen at CWI Amsterdam as the analytical counterpart to SQLite.
DuckLake
DuckLake is an open lakehouse format from the DuckDB team (DuckLabs), storing metadata in a SQL catalog database (SQLite, PostgreSQL, MySQL, DuckDB) and data in Iceberg-compatible Parquet files. Launched May 2025, v1.0 April 2026, MIT-licensed.
Dueling network architectures
The dueling network architecture is a deep reinforcement learning design introduced by Google DeepMind in 2015, splitting a Q-network into value and advantage streams that are combined into action values.
Dung beetle optimization algorithm
The dung beetle optimization algorithm is a swarm-based metaheuristic introduced by Jiankai Xue and Bo Shen in 2022 that mimics dung beetle behaviors to solve optimization problems.
Dutch national flag problem
The Dutch national flag problem, posed by Edsger Dijkstra in 1973, is sorting an array of three values, such as red, white, and blue, in one pass in place.
DVS study
DVS study: research on the Dynamic Vision Sensor, an event camera reporting pixel-level brightness changes at microsecond resolution. Covers origins (Mahowald and Mead silicon retina), tracking, driving datasets, and the CARLA sim-to-real gap.
Dwarf mongoose optimization
Dwarf mongoose optimization (DMO) is a swarm-based metaheuristic, introduced by Agushaka, Ezugwu, and Abualigah in 2022, that mimics dwarf mongoose foraging and sleeping-site behavior to solve optimization problems.
Dynamic community detection
Dynamic community detection is a family of network analysis algorithms that tracks how communities of densely connected nodes form, change, merge, and split over time in time-varying graphs.
Dynamic graph learning
Dynamic graph learning, also known as dynamic graph representation learning, is a machine learning approach that learns representations of graphs whose nodes and edges change over time.
Dynamic multi-objective optimization
Dynamic multi-objective optimization (DMO) is the study of methods that track and update Pareto-optimal trade-off solutions while a problem's objectives or constraints change over time, using evolutionary algorithms.
Dynamic programming
Dynamic programming is an algorithm design method, developed by Richard Bellman at RAND in the early 1950s, that solves optimization problems by breaking them into overlapping subproblems and reusing stored results.
Dynamic relaxation
Dynamic relaxation is an iterative numerical method that solves a structure's static equilibrium equations by simulating a damped dynamic process, used mainly for form-finding of tension structures.
Dynamic state estimation
Dynamic state estimation is a family of filtering methods that estimate the time-varying hidden state of a dynamic system from noisy measurements, one time step at a time.
Dynamic time warping
Dynamic time warping, or DTW, is a similarity measure for time series that finds the optimal nonlinear alignment between two sequences, developed by Sakoe and Chiba for speech recognition.
Dynamic window approach
The dynamic window approach (DWA) is a local obstacle-avoidance method for mobile robots, introduced by Fox, Burgard, and Thrun in 1997 and used as the default local planner in the ROS navigation stack.
E(3)-equivariant message passing
E(3)-equivariant message passing is a graph neural network design in which features transform predictably under rotations, translations, and reflections in 3D space, used chiefly to model molecules and materials.
E(n)-Equivariant Graph Neural Network
An E(n)-equivariant graph neural network (EGNN) is a graph neural network whose outputs transform predictably under rotations, translations, and reflections, introduced by Satorras, Hoogeboom, and Welling at ICML 2021.
Early exiting
Early exiting is a neural network inference technique with intermediate classifiers at multiple depths, so each input exits at the shallowest point where confidence suffices, cutting computation.
Early stopping
Early stopping is a machine learning technique that halts training when error on a held-out validation set begins to rise, returning the best weights; it acts as implicit regularization.
Echo state network
An echo state network (ESN) is a recurrent neural network architecture introduced by Herbert Jaeger in 2001, in which only the readout connections are trained.
Edgar F. Codd
Edgar F. Codd, known as Ted Codd, was an IBM computer scientist whose 1970 relational model became the foundation of most modern databases, earning the 1981 Turing Award.
Edge detection
Edge detection, also known as border detection, is an image-processing technique that locates sharp intensity changes in a digital image, corresponding to object boundaries and scene structure.
Edge enhancement
Edge enhancement is an image processing technique that increases contrast along object boundaries in a digital image, making edge detail more detectable by people and computer vision algorithms.
Edit distance
Edit distance, also called Levenshtein distance, measures how different two strings are through the minimum number of character insertions, deletions, and substitutions needed to transform one into the other.