Artificial intelligence and data

Superpoint

SuperPoint is a self-supervised, fully-convolutional neural network that detects interest points and computes descriptors in a single forward pass, introduced by Magic Leap in 2018 for SLAM and camera calibration.

Supervised contrastive learning

Supervised contrastive learning (SupCon) is a machine learning technique that pulls together representations of same-label samples and pushes apart different ones, introduced by Khosla and colleagues in 2020.

Supervised learning

Supervised learning, also called supervised machine learning, is a machine-learning paradigm where a model trains on input-output pairs, like labeled spam emails, covering regression and classification tasks.

Supervised object detection

Supervised object detection trains a model on images or point clouds with labeled objects, outputting a localized bounding box and class label for each object, from Faster R-CNN to YOLO.

Support vector data description

Support vector data description (SVDD) is a one-class classification method proposed by Tax and Duin in 1999 that encloses target data in a hypersphere to detect outliers.

Support vector machine

A support vector machine (SVM) is a supervised machine learning method that classifies data by finding a hyperplane maximizing the margin between classes; it is also used for regression and outlier detection.

Support vector regression

Support vector regression (SVR) is a kernel-based supervised learning method that predicts continuous values by fitting a function within an ε-tube of the training targets.

Surface rendering

Surface rendering is a volume visualization technique that converts 3D scalar data into an image by extracting a polygonal isosurface and shading it, typically with marching cubes.

GeneralOct 26, 2026

Surrogate key

Surrogate key: warehouse-generated artificial identifier (usually a sequential integer) replacing a source natural key as a dimension table's primary key; enables multi-source consolidation and SCD type 2 history, with the date dimension a YYYYMMDD exception.

Surrogate model

A surrogate model is a computationally cheap approximation of an expensive simulator, built from a modest number of training evaluations and used for prediction, optimization, and sensitivity analysis.

Surrogate optimization

Surrogate optimization finds optima of expensive black-box functions by building a cheap approximate model, the surrogate, to decide where to evaluate next; Bayesian optimization is the most common form.

Surrogate-based optimization

Surrogate-based optimization (SBO) is an engineering optimization strategy that replaces a costly model, such as a CFD simulation, with a cheap surrogate approximation to find optimized designs with fewer expensive evaluations.

Survey propagation

Survey propagation is a message-passing algorithm from statistical physics, introduced by Mézard and Zecchina in 2002 to solve hard random K-SAT instances near the satisfiability threshold.

Swarm intelligence

Swarm intelligence, also known as swarm theory, is the collective behavior emerging from simple local interactions among agents, inspiring optimization algorithms such as particle swarm and ant colony optimization.

Swarm learning (machine learning)

Swarm learning (SL) is a decentralized machine learning framework in which nodes train a shared model on local data, coordinated through blockchain instead of a central server.

Swin Transformer

The Swin Transformer is a vision transformer introduced by Microsoft Research in 2021, computing attention in shifted local windows for image classification, detection, and segmentation.

Swish (activation function)

Swish is a neural network activation function, f(x) = x·σ(βx), discovered by automated search at Google Brain in 2017 and used in architectures like EfficientNet and MobileNetV3.

SWISS-PROT

SWISS-PROT is a manually curated protein sequence database created in 1986 by Amos Bairoch at the University of Geneva, and since 2002 it has served as the reviewed, expert-annotated section of UniProtKB.

Sybase

Sybase, Inc. was an American enterprise software company founded in 1984 that built one of the first client/server relational databases and was acquired by SAP in 2010 for about $5.8 billion.

Symbiotic organisms search

Symbiotic organisms search (SOS) is a parameter-free metaheuristic optimization algorithm, introduced by Cheng and Prayogo in 2014, that improves candidate solutions through mutualism, commensalism, and parasitism phases.

Symmetry reduction

Symmetry reduction is a model checking technique that identifies states related by symmetries, such as permutations of identical processes, and verifies a smaller quotient structure instead.

Synaptic Intelligence

Synaptic Intelligence (SI) is a regularization technique against catastrophic forgetting in continual learning for neural networks, introduced by Zenke, Poole, and Ganguli at ICML in 2017.

Synchrosqueezing transform

The synchrosqueezing transform (SST) is a time-frequency analysis method that sharpens wavelet or short-time Fourier representations by reassigning spectral energy along the frequency axis, remaining invertible so individual oscillatory modes can be reconstructed.

Syndrome extraction

Syndrome extraction is the quantum error correction procedure that measures stabilizer operators on an encoded block of qubits to obtain an error syndrome without revealing the logical information.

Syntactic parsing

Syntactic parsing is the NLP task of recovering a sentence's grammatical structure from text, either as a phrase-structure tree or as labeled dependency relations between words.

GeneralOct 26, 2026

Synthetic Data Vault

Synthetic Data Vault (SDV): open-source Python library from MIT's Data to AI Lab (2016, Patki, Wedge, Veeramachaneni) that builds generative models of relational databases to create realistic synthetic tabular, relational, and time-series data; now developed by DataCebo.