61,984 articles
General-purpose input/output
General-purpose input/output (GPIO), also known as general purpose IO, is a digital pin on an integrated circuit that software configures as input or output to monitor switches and drive LEDs.
General-purpose machine gun
A general-purpose machine gun (GPMG) is a belt-fed, air-cooled machine gun that serves in light, medium, and mounted roles, first exemplified by Germany's MG34 of the 1930s.
General-purpose programming language
A general-purpose programming language is a programming language designed to express programs across a wide range of application domains rather than one narrow problem domain; familiar examples include C, Java, Python, and JavaScript.
Generalization bound
A generalization bound is a high-probability upper limit on the gap between a learning algorithm's training error and its expected error on new data, typically empirical error plus a complexity term.
Generalization error
Generalization error is the difference between a model's population risk and its empirical risk on its training data, measuring how performance on unseen data departs from measured training performance, with bounds central to statistical learning theory.
Generalized frequency-division multiplexing
Generalized frequency-division multiplexing (GFDM) is a non-orthogonal multi-carrier modulation scheme developed at TU Dresden as a 5G waveform candidate, generalizing OFDM with flexible pulse shaping.
Generalized impedance control
Generalized impedance control (GIC) is a robot control method, proposed by Lee and Lee in 1991, that extends impedance control so a robot can track force as well as motion.
Generalized intersection over union
Generalized intersection over union (GIoU) is a similarity measure and regression loss for shapes, extending IoU so it gives a usable gradient for non-overlapping boxes.
Generalized iterative closest point
Generalized iterative closest point (Generalized-ICP, GICP) is a probabilistic variant of the ICP algorithm for aligning two point clouds, published at Robotics: Science and Systems in 2009.
Generalized MPLS
Generalized MPLS (GMPLS) is an extension of the MPLS architecture that extends its control plane to switching technologies that do not forward data by packet header, such as SONET/SDH, wavelengths, and fibers.
Generalized Multi-Protocol Label Switching
Generalized Multi-Protocol Label Switching (GMPLS) is an IETF extension of the MPLS control plane, defined in RFC 3945, that adds switching of time slots, wavelengths, and fibers.
Generalized regression neural network
A generalized regression neural network (GRNN) is a radial-basis neural network for regression and function approximation, introduced by D.F. Specht in 1991, with one-pass training and only a bandwidth to tune.
Generalized selection combining
Generalized selection combining (GSC), or hybrid selection/maximum ratio combining, is a diversity technique in which wireless receivers combine the strongest subset of available signal branches, balancing performance and complexity.
Generalized spatial modulation
Generalized spatial modulation (GSM) is a MIMO transmission scheme where a transmitter activates only some of its antennas, with the active antenna indices carrying information.
Generate Capital
Generate Capital is a San Francisco-based sustainable infrastructure investment company, founded in 2014, that builds, finances, owns, and operates distributed energy and resource assets across North America.
Generation IV reactor
A Generation IV reactor is a fourth-generation nuclear fission reactor design chosen by the Generation IV International Forum for collaborative development, targeted for deployment around 2030.
Generative adversarial imitation learning
Generative adversarial imitation learning (GAIL) is a machine learning method that trains agents to imitate expert behavior, introduced by Jonathan Ho and Stefano Ermon in 2016.
Generative adversarial network
A generative adversarial network (GAN) is a machine learning framework in which a generator producing synthetic samples and a discriminator judging real versus generated train in a minimax game.
Generative Agents
Generative agents are software agents powered by large language models that store memories, reflect, and plan, introduced by Joon Sung Park and colleagues at Stanford and Google in April 2023.
Generative AI pornography
Generative AI pornography, also called AI pornography, is sexually explicit imagery or video made with generative artificial intelligence, ranging from synthetic content to nonconsensual deepfakes of real people.
Generative AI Profile
The Generative AI Profile, designated NIST AI 600-1, is a voluntary guide released by NIST in July 2024 that adapts its AI Risk Management Framework to generative AI risks.
Generative artificial intelligence
Generative artificial intelligence, also known as GenAI, is AI that generates new content such as text, images, video, and audio, reaching mass public use in late 2022.
Generative design
Generative design is a computational engineering method that uses algorithms, combining optimization, machine learning, and simulation, to automatically produce many design alternatives meeting specified goals and constraints.
Generative engine optimization
Generative engine optimization (GEO), also called Answer Engine Optimization, structures web content so generative AI answer engines like ChatGPT and Google's AI Overviews cite it, formalized at a 2024 ACM conference.
Generative model
A generative model, or generative statistical model, is a statistical model that learns the probability distribution of data, letting it generate new samples, score examples, and classify via Bayes' rule.
Generative pre-trained transformer
A generative pre-trained transformer (GPT) is a large language model built on a transformer decoder, pre-trained to predict the next token; OpenAI introduced the name in 2018.
Generative Replay
Generative replay, introduced as Deep Generative Replay at NIPS in 2017, is a continual learning technique where a generative model synthesizes pseudo-samples of past tasks to prevent catastrophic forgetting.
Generator circuit breaker
A generator circuit breaker (GCB) is a switching device between a power plant generator and its step-up transformer, rated above 1 kV and designed to interrupt very large, heavily asymmetrical fault currents.
Generic Attribute Profile
The Generic Attribute Profile (GATT) is a Bluetooth specification, built on the Attribute Protocol, that defines how devices expose and discover services and read, write, and notify characteristic values.
Generic programming
Generic programming, also called genericity, is a programming style in which algorithms and data structures are written once, parameterized over types, while keeping compile-time type checking.