Semantic memory - Semantic memory is memory for facts, concepts and meanings, knowing what things are and how they relate, as distinct from episodic memory for specific...
Semi-supervised learning - Semi-supervised learning is training that combines a small amount of labeled data with a large amount of unlabeled data, using the structure of the...
Sentiment analysis - Sentiment analysis is the automated reading of text to judge the attitude it expresses, typically positive, negative or neutral, so that opinion at scale...
Sequence-to-sequence task - A sequence-to-sequence task is one where both input and output are ordered sequences: a sentence becomes a translation, a question becomes an answer, a...
Sequential Feature Selection - Sequential Feature Selection is a family of feature selection methods that build the feature set step by step, adding the most helpful feature each round...
Shrinkage - Shrinkage is the deliberate pulling of estimated values toward a center, typically toward zero or a group average, trading a little bias for a large...
Similarity learning - Similarity learning trains a model to judge how alike or related two objects are for a particular task.
Simultaneous autoregression - Simultaneous autoregression is a spatial statistics model where each location's value is predicted from the values of its neighboring locations at the same...
Single program / multiple data - Single program / multiple data, usually shortened to SPMD, is a way of organizing parallel computing in which several processors run the same program on...
Situated - In artificial intelligence, situated describes an agent whose behavior is embedded in and shaped by interaction with an environment.
Situated approach (artificial intelligence) - The situated approach in artificial intelligence designs and studies agents through their ongoing interaction with an environment.
Sketching - In similarity search and clustering, sketching uses compact summaries or preliminary groupings to reduce the number of expensive comparisons between items.
Skill chaining - Skill chaining is a method for discovering and connecting reusable skills so that completing one skill puts an agent in a state where another can begin.
Skip-gram - A skip-gram is a sequence of words taken from text while allowing gaps between the selected words.
Slopaganda - Slopaganda is an emerging term for the use of mass-produced, often low-quality AI-generated content to shape an information environment for propagandistic...
Soft clustering - Soft clustering describes an item using degrees of membership in several clusters instead of assigning it only to one group.
Soft independent modeling of class analogies - Soft independent modeling of class analogies, usually abbreviated SIMCA, is a class-modeling approach that builds a separate principal-component model for...
Softmax - Softmax converts a list of numerical scores into positive values that sum to one.
Software agent - A software agent is a software system that acts within an environment on behalf of a user or another system, with some degree of autonomy.
Solomonoff's theory of inductive inference - Solomonoff's theory of inductive inference is a mathematical framework for predicting future observations by combining computable explanations of past...
Sparse feature - A sparse feature is a feature whose expanded representation contains mostly zeros or inactive values.
Sparse PCA - Sparse PCA is a family of principal-component methods that encourage each component to depend on relatively few original variables.
Sparse representation - A sparse representation records data using relatively few active values compared with the number of possible positions or components.
Spatial Analysis of Principal Components - Spatial analysis of principal components, commonly called spatial PCA or sPCA, is a multivariate method that combines variation in measurements with spatial...
Spatial embedding - A spatial embedding is a numerical representation of spatial information designed for use in a learning or analysis system.
Spatial intelligence (artificial intelligence) - Spatial intelligence in artificial intelligence refers to capabilities for perceiving, representing, and reasoning about objects and environments in space.
Spectral clustering - Spectral clustering groups items using the structure of a similarity graph.
Spike-and-slab regression - Spike-and-slab regression is a Bayesian approach that uses a mixture prior for regression coefficients.
Splitter - In decision-tree training, a splitter is the procedure that selects the condition used to divide examples at a node.
Spreading activation - Spreading activation is a process in which activity assigned to one node in a network influences connected nodes.
Stacked generalization - Stacked generalization, often called stacking, combines predictions from several models using another model that learns how to combine them.
Staged training - Staged training trains a machine-learning model through a planned sequence of distinct phases.
State - In reinforcement learning and agent systems, a state describes the situation relevant to deciding what happens next.
Statistical classification - Statistical classification is the task of assigning an observation to one or more categories using a model informed by data.
Statistical learning theory - Statistical learning theory studies how and when a model learned from finite data can perform well on new observations.
Statistical relational learning - Statistical relational learning is a family of methods that learn and reason under uncertainty while representing relationships among entities.
Step size - In optimization, step size controls how far an update moves along a chosen search direction.
STIT logic - STIT logic is a family of formal logics for reasoning about agency: an agent “sees to it that” some statement is true.
Stochastic program - A stochastic program is a statistical model expressed as a procedure that makes random draws.
Stochastic variance reduction - Stochastic variance reduction is a collection of optimization techniques that reduce randomness in estimated gradients while retaining much of the...
Streaming Feature Pipeline - A streaming feature pipeline continuously processes incoming events into features that machine-learning systems can use.
Stride - Stride is the distance a sliding operation moves between successive positions in an input.
Struc2vec - Struc2vec is a graph representation learning method designed to place nodes with similar structural roles near one another in a vector space.
Structural equation modeling - Structural equation modeling, or SEM, is a statistical framework for representing and estimating relationships among variables through linked equations.
Structured sparsity regularization - Structured sparsity regularization encourages a model to use a limited set of parameters in patterns that reflect known relationships.
Sufficient dimension reduction - Sufficient dimension reduction seeks a smaller representation of predictors that preserves all their information about a specified response.
Superintelligence ban - A superintelligence ban is a proposed prohibition on developing, deploying, or otherwise enabling AI systems that exceed a defined superintelligence threshold.
Supervised Clustering - Supervised clustering groups objects using guidance from known labels.