3,135 articles
FrameNet
FrameNet is a lexical database of English organized around semantic frames, established in 1997 by Charles J. Fillmore in Berkeley and used for semantic role labeling in natural language processing.
Freebase (knowledge base)
Freebase was a large, collaboratively created graph database of general human knowledge developed by Metaweb, which Google acquired in 2010 and shut down in 2016.
Fruit fly optimization algorithm
The fruit fly optimization algorithm (FOA) is a swarm intelligence metaheuristic for numerical optimization, introduced by Wen-Tsao Pan in 2011 and inspired by how fruit flies forage by smell and then sight.
Full Self-Driving
Full Self-Driving (FSD), renamed FSD (Supervised), is Tesla's Level 2 driver assistance system, first released in 2020, which navigates city streets while the driver supervises constantly.
Fully convolutional network
A fully convolutional network (FCN) is a neural network architecture for image segmentation that replaces fully connected layers with convolutions, producing dense per-pixel predictions from inputs of any size.
Functional decomposition
Functional decomposition is a method that breaks a complex function into simpler subfunctions computed separately and recombined by composition, fundamental in logic synthesis and FPGA design.
Functional dependency
A functional dependency in relational database theory, written X → Y, is a constraint where one set of attributes determines another, underpinning keys, Armstrong's axioms, and normalization.
Fundamental matrix (computer vision)
The fundamental matrix is a 3 × 3 rank-2 matrix in computer vision encoding the epipolar geometry between two uncalibrated camera views, satisfying x'TFx = 0 for corresponding points.
Fundamentals of Data Engineering
Fundamentals of Data Engineering: Plan and Build Robust Data Systems (2022, O'Reilly), by Joe Reis and Matt Housley, a 450-page beginner book organizing data engineering around a five-stage lifecycle and six undercurrents.
Fuzzy cognitive map
A fuzzy cognitive map (FCM) is a graph-based modeling method in which weighted, signed causal links connect concepts and simulations support decision making in complex systems.
Fuzzy cognitive mapping
Fuzzy cognitive mapping is a modeling method that represents concepts and weighted causal relationships as a graph, simulating how activation spreads to support scenario analysis and decisions.
Fuzzy entropy
Fuzzy entropy is a measure of the degree of fuzziness of a fuzzy set, defined by De Luca and Termini in 1972 without reference to probability.
Fuzzy inference system
A fuzzy inference system is a computational method that maps inputs to outputs through if-then rules over fuzzy sets, used in control systems such as cement kilns since 1978.
Fuzzy k-means clustering
Fuzzy k-means clustering, also called fuzzy c-means, is a soft clustering algorithm that assigns each data point fractional memberships in every cluster rather than one hard label.
Fuzzy linear programming
Fuzzy linear programming (FLP) treats the parameters, constraints, or objectives of linear programming models as fuzzy, so constraints and goals are satisfied to varying degrees.
Fuzzy rough sets
Fuzzy rough sets are a hybrid mathematical model combining fuzzy set theory's graded membership with rough set theory's approximations, introduced by Dubois and Prade in 1990 and used mainly for feature selection.
Fuzzy time series
Fuzzy time series is a forecasting method, introduced by Song and Chissom in the early 1990s, whose observations are fuzzy sets or linguistic values rather than crisp numbers.
GA-BP neural network
A GA-BP neural network is a hybrid training method in which a genetic algorithm finds good initial weights and thresholds that backpropagation then fine-tunes by gradient descent.
Gabor filter
A Gabor filter is a linear image filter, a sinusoidal wave modulated by a Gaussian envelope, that measures local orientation and frequency in images for texture analysis and biometric recognition.
Gabor transform
The Gabor transform is a time-frequency analysis method, the short-time Fourier transform taken with a Gaussian window, showing how a signal's frequencies change over time.
Gale–Shapley algorithm
The Gale–Shapley algorithm, also called deferred acceptance, is a procedure introduced by David Gale and Lloyd Shapley in 1962 that always yields a stable matching between two groups.
Garante per la protezione dei dati personali
The Garante per la protezione dei dati personali, commonly Garante Privacy, is Italy's independent data protection authority, established by the 1996 privacy law and based at Piazza Venezia in Rome.
Gas kinetic scheme
The gas kinetic scheme (GKS) is a finite-volume computational fluid dynamics method that computes numerical fluxes from the time-evolution solution of the Boltzmann equation rather than a Riemann solver.
Gate model (quantum computing)
The gate model is a model of quantum computation in which an algorithm is a sequence of quantum logic gates acting on qubits, ending in a measurement.
Gated recurrent unit
The gated recurrent unit (GRU) is a recurrent neural network cell introduced in 2014 by Kyunghyun Cho and colleagues as a streamlined alternative to the LSTM.
Gaussian blur
Gaussian blur, also called Gaussian smoothing, is an image-processing operation that replaces each pixel with a weighted average of its neighborhood, reducing noise but blurring edges.
Gaussian boson sampling
Gaussian boson sampling (GBS) is a photonic quantum computing protocol, proposed in 2017, that sends squeezed light through a linear optical interferometer and samples photon-number patterns, a #P-hard task demonstrating quantum advantage.
Gaussian filtering
Gaussian filtering is a signal and image processing method that smooths data and suppresses noise by convolving it with a Gaussian kernel, at the cost of blurring fine detail.
Gaussian quadrature
Gaussian quadrature, also called Gaussian integration, is a numerical integration method introduced by Carl Friedrich Gauss in 1814, exact for polynomials of degree 2n − 1 with n nodes.
Gaussian splatting
Gaussian splatting is a 3D scene representation and rendering method that models scenes as anisotropic Gaussian primitives, optimized from photographs for real-time novel view synthesis.