All articles A–Z
519,064 articles
Sparky Anderson
Sparky Anderson (George Lee Anderson, 1934-2010), American MLB manager of the Cincinnati Reds and Detroit Tigers; won World Series in 1975, 1976, and 1984, first manager to win it in both leagues, 2,194 wins, Hall of Fame 2000.
SPARQL
SPARQL (SPARQL Protocol and RDF Query Language) is the W3C-standardized query language and associated HTTP protocol for querying RDF graph data, a W3C Recommendation since 2008 and the standard query language for Linked Data.
Sparro
Sparro, also spelled Sparro (Shibumi), is Phil Leduc's 2011 three-in-a-row game for the Shibumi marble-pyramid system, adapting Connect Four with 12 balls per player and non-flat lines; not the Steam game Sparrow God.
Sparrow
Sparrow: small seed-eating passerines, chiefly the house sparrow (Passer domesticus), the world's most abundant bird at 1.6 billion, human-associated, IUCN Least Concern but declining in North America and Europe.
Sparrow Lacus
Sparrow Lacus is a lake of liquid hydrocarbons near Titan's north pole, about 81 km across, named after Sparrow Lake in Ontario and approved by the IAU in 2007.
Sparrow search algorithm
The sparrow search algorithm (SSA) is a swarm intelligence metaheuristic introduced in 2020 that mimics sparrow flock foraging and anti-predation behavior to find global optima.
Sparrow-and-rat surcharge
The sparrow-and-rat surcharge (雀鼠耗) was an extra levy on grain tax in the Five Dynasties and Ten Kingdoms, nominally to cover grain eaten by sparrows and rats in storage.
Sparrows
Sparrows (1926) is a Mary Pickford silent melodrama directed by William Beaudine, originally titled Scraps, about orphans escaping a swamp baby farm; premiered May 1926, restored by the Library of Congress, added to the National Film Registry in 2025.
Sparse approximation
Sparse approximation is the task of representing a signal as a combination of a small number of elements from a larger dictionary, underlying compression, denoising, and inverse-problem regularization.
Sparse array design
Sparse array design selects nonuniform element positions and excitation weights for an antenna array, meeting beamforming or direction-finding goals with fewer elements than a filled uniform array.
Sparse autoencoder
A sparse autoencoder is an autoencoder whose training adds a sparsity penalty on the code layer, keeping few units active; it underlies unsupervised feature learning and language model interpretability.
Sparse autoencoders for interpretability
Sparse autoencoders are an unsupervised technique that decomposes a neural network's activations into sparse, interpretable features, introduced for language models in 2023 by Cunningham et al. and Anthropic.
Sparse Bayesian learning
Sparse Bayesian learning is a Bayesian machine learning method that fits regression and classification models by pruning irrelevant basis functions, producing sparse models with probabilistic outputs.
Sparse canonical correlation analysis
Sparse canonical correlation analysis (sparse CCA) is a multivariate statistical method finding sparse, maximally correlated linear combinations of two variable sets, enabling feature selection in high-dimensional paired data.
Sparse channel estimation
Sparse channel estimation is a wireless signal processing method that recovers radio channel parameters from far fewer pilot measurements than classical least-squares training, by exploiting channel sparsity with compressed sensing algorithms.
Sparse code multiple access
Sparse code multiple access (SCMA) is a code-domain non-orthogonal multiple access technique proposed at Huawei in 2013, letting several users share the same radio resources.
Sparse decomposition (signal processing)
Sparse decomposition is a signal processing method representing a signal as a linear combination of a few atoms from a redundant dictionary, used in compressed sensing and machine learning.
Sparse estimation (statistics)
Sparse estimation is a class of statistical methods that fit high-dimensional models by penalizing coefficients so many are exactly zero, as in Robert Tibshirani's 1996 lasso.
Sparse feature-based mapping
Sparse feature-based mapping is a robot mapping approach that represents the environment with a small set of landmarks instead of a dense grid or point cloud.
Sparse Fourier transform
A sparse Fourier transform (SFT) is an algorithm that computes a k-sparse approximation of the discrete Fourier transform faster than the fast Fourier transform for frequency-sparse signals.
Sparse grid
A sparse grid is a numerical construction that represents high-dimensional functions on a subset of a full tensor-product grid, using the Smolyak algorithm, enabling quadrature, interpolation, and surrogate modeling in tens of dimensions.
Sparse matrix
A sparse matrix, also known as a sparse array, is a matrix in which most entries are zero; exploiting sparsity makes solving systems with millions of unknowns practical.
Sparse non-negative matrix factorization
Sparse non-negative matrix factorization (sparse NMF) decomposes a non-negative data matrix into two non-negative factors with user-set sparseness constraints, used in speech separation and hyperspectral unmixing.
Sparse optimization
Sparse optimization is a class of optimization methods that seek solutions with few nonzero variables, using sparsity-inducing penalties or constraints such as the lasso and basis pursuit.
Sparse PCA
Sparse PCA is a dimension-reduction method that performs principal component analysis under sparsity constraints, so each component combines only a few of the original variables.
Sparse principal component analysis
Sparse principal component analysis (sparse PCA) is a statistical method that makes PCA components depend on only a few variables, trading some explained variance for interpretability.
Sparse regression
Sparse regression fits a linear model while forcing most coefficients to be exactly zero, delivering both prediction and variable selection on high-dimensional data where ordinary least squares fails.
Sparse Transformer
The Sparse Transformer is a neural network architecture introduced at OpenAI in April 2019, replacing quadratic self-attention with sparse patterns that cut cost from O(n²) to O(n√n).
Sparse upcycling
Sparse upcycling is a training technique for large language models that converts a trained dense model into a mixture-of-experts model, recovering performance with about 50% of the original pretraining cost.
Sparse-view CT reconstruction
Sparse-view CT reconstruction is a computed tomography method that recovers diagnostic-quality images from far fewer projection angles than a standard scan, reducing radiation dose and acquisition time.