Singularity - In discussions of AI's long-term future, the singularity is a hypothesized transition in which greater-than-human intelligence drives accelerating...
Sink (pipelines) - A sink is the destination stage or component to which a data pipeline writes its output.
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.
Situated robotics - Situated robotics studies and designs robots as agents whose behavior arises through ongoing interaction with their environment.
Situation calculus - Situation calculus is a logical framework for describing actions and reasoning about how their effects change the world.
Size invariance - Size invariance is an image-classification system's ability to preserve the correct class when the apparent size or resolution of the relevant image content...
Size (statistics) - In hypothesis testing, the size of a test is the largest, more precisely the supremum, of its rejection probability over all parameter values allowed by the...
Skeletonization - In robot path planning, skeletonization represents navigable configuration space using a graph of selected configurations and feasible connections.
Sketching - In similarity search and clustering, sketching uses compact summaries or preliminary groupings to reduce the number of expensive comparisons between items.
Skewness - Skewness describes asymmetry in a distribution.
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 connection - A skip connection is a neural-network connection that carries information past one or more intervening layers to a later part of the network.
Skip-gram - A skip-gram is a sequence of words taken from text while allowing gaps between the selected words.
Skip-gram negative sampling - Skip-gram negative sampling, commonly abbreviated SGNS, is a method for learning word vectors by distinguishing observed word-context pairs from randomly...
Skolem constant - A Skolem constant is a fresh constant symbol introduced to represent an existential witness when that witness does not depend on universally quantified...
Skolemization - Skolemization is a transformation of first-order logic formulas that removes existential quantifiers by introducing fresh constants or functions for their...
Sky computing - Sky computing is a vision of using resources across cloud providers through a more unified layer that can place workloads according to requirements and...
Skyline operator - A skyline operator returns the records that are not dominated by another record across a chosen set of preference dimensions.
Slack - In scheduling, slack is the amount of timing flexibility available to an activity under the schedule's assumptions.
Slice - A slice selects part of a sequence using a start position, a stopping boundary and an optional step. In Python, the usual notation is sequence[start:stop:step].
Slice sampling - Slice sampling is a Markov chain Monte Carlo method that samples a distribution by introducing an auxiliary height beneath its unnormalized density curve.
Sliced inverse regression - Sliced inverse regression, or SIR, is a supervised dimension-reduction method that seeks informative linear combinations of predictors for explaining a...
Sliced score matching - Sliced score matching is a method for learning a probability distribution's score by comparing score vectors along random directions.
Sliding window - A sliding window is a fixed-size region moved across an input so that a repeated operation can be applied at successive positions.
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...
Slot filling - Slot filling is the process of identifying values for named fields in a structured representation of a user’s request or another piece of text.
SMA* - SMA*, or Simplified Memory-Bounded A*, is a heuristic search algorithm that works within a memory limit.
Small data - Small data refers to data of a limited, manageable scale in its context.
Small-scale learning - Small-scale learning refers to machine learning with a relatively limited training dataset.
Small-world - A small-world network is a graph that combines strong local clustering with relatively short routes between nodes across the network.
Smallest grammar problem - The smallest grammar problem asks for the most compact context-free grammar that generates exactly one specified string.
Smart data capture - Smart data capture is an umbrella term for using automated sensing and interpretation to turn information from the physical world into usable digital data.
SMDP - SMDP stands for semi-Markov decision process: a model for sequential decisions in which the time between decision points can vary.
Smearing retransformation - Smearing retransformation is a method for estimating an expected response on its original scale after fitting a regression on a transformed scale.
Smoothed Bellman error embedding - Smoothed Bellman error embedding, or SBEED, is a reinforcement-learning method that combines an entropy-smoothed Bellman equation with a primal-dual...
Smoothing - Smoothing refers to methods that moderate unstable estimates or use surrounding information to estimate an underlying quantity.
Smoothing inference with twisted objectives - Smoothing inference with twisted objectives, or SIXO, is a method for learning probabilistic sequence models using sequential Monte Carlo targets that...
Smoothing spline - A smoothing spline estimates a smooth relationship by balancing fit to observed data against a penalty for excessive curvature.
Smoothness term - A smoothness term is part of an optimization objective that penalizes specified kinds of variation in an estimated image, field, or set of labels.
SMOTE - SMOTE stands for Synthetic Minority Over-sampling Technique.
Snapshot isolation - Snapshot isolation is a transaction-isolation approach in which a transaction reads from a consistent snapshot of committed data, together with its own...
Sobel edge detector - A Sobel edge detector uses small filters to estimate how image intensity changes horizontally and vertically.
Sobel test - The Sobel test is a normal-approximation test of an indirect effect expressed as the product of two estimated regression paths.
Social cloud computing - Social cloud computing is a resource-sharing model that uses relationships within a social network to help organize access to computing, storage or other...
Social cognitive optimization - Social cognitive optimization, or SCO, is a population-based optimization method inspired by learning from other people's examples.