61,984 articles
Self-organizing network
A self-organizing network (SON) is a set of automated functions for planning, configuring, optimizing, and healing mobile radio access networks, standardized by 3GPP beginning with LTE in Release 8.
Self-piercing rivet
A self-piercing rivet (SPR) is a semi-tubular fastener driven by a punch through upper sheets, flaring in a die to form a mechanical interlock without a pre-drilled hole or heat.
Self-play
Self-play is a reinforcement learning method in which an agent improves by playing against copies of itself, the paradigm behind AlphaGo Zero, AlphaZero, and MuZero.
Self-play and self-rewarding alignment
Self-play and self-rewarding alignment are post-training methods where a language model generates candidate responses, judges them itself, and trains its next iteration on the resulting preferences.
Self-propagating high-temperature synthesis
Self-propagating high-temperature synthesis (SHS) is a combustion-based method for making ceramics, intermetallics, and other refractory compounds, discovered in the Soviet Union in 1967, in which a reaction front moves through compacted powder without a furnace.
Self-propelled artillery
Self-propelled artillery, also called a self-propelled gun, is a howitzer mounted on a tracked or wheeled vehicle, able to displace quickly after firing to avoid counter-battery fire.
Self-RAG
Self-RAG is a fine-tuning method for large language models, introduced in 2023, in which the model itself decides when to retrieve passages and critiques them using reflection tokens.
Self-refine
Self-Refine is a prompting-time method for large language models where a single model generates, critiques, and revises its own outputs, improving performance by about 20% on average without any training.
Self-refine and iterative prompting
Self-refine is an inference-time method, introduced in March 2023, in which a language model acts as generator, critic, and refiner, improving its output without additional training.
Self-replicating spacecraft
A self-replicating spacecraft, often called a von Neumann probe, is a hypothetical craft that harvests local materials to build copies of itself, enabling exponential exploration.
Self-rewarding language models
Self-rewarding language models are language models trained to judge their own outputs and improve through iterative DPO, introduced by Meta AI researchers in a January 2024 paper.
Self-sealing fuel tank
The self-sealing fuel tank is a fuel container, typically a flexible bladder, that seals small punctures on its own; the US Navy began developing the technology in 1940.
Self-service analytics
Self-service analytics (SSA, self-service BI) is business intelligence that lets nontechnical users access, analyze and visualize data via tools like Tableau and Power BI, supported by governed data pipelines and central IT.
Self-signed certificate
A self-signed certificate is an X.509 certificate signed with its own private key, so its Subject and Issuer are the same; it is trusted only out of band.
Self-supervised monocular depth estimation
Self-supervised monocular depth estimation is a computer vision method that trains a network to predict per-pixel depth from a single image without ground-truth labels, using photometric consistency.
Self-tapping screw
The self-tapping screw, also called a tapping screw or Tek screw, is a fastener that cuts or forms its own mating thread in a pre-drilled hole, eliminating the need for a nut.
Self-verification (prompting)
Self-verification (prompting) is a technique where a large language model checks its own candidate answers, re-deriving the question's conditions from each answer and ranking them by a verification score before answering.
SelfCheckGPT
SelfCheckGPT is a black-box, zero-resource method for detecting hallucinations in large language models, proposed at the University of Cambridge in 2023, which checks sampled responses for consistency.
Selim A. Chacour
Selim A. Chacour is an American mechanical engineer who founded American Hydro Corporation in 1986 and was elected to the National Academy of Engineering in 2009.
Selimiye Mosque
The Selimiye Mosque (Selimiye Camii) is a 16th-century Ottoman imperial mosque in Edirne, Turkey, commissioned by Sultan Selim II and built by Mimar Sinan between 1568 and 1575.
Selimiye Mosque and its Social Complex
The Selimiye Mosque and its Social Complex is a UNESCO World Heritage mosque in Edirne, Turkey, designed by Sinan and built from 1568 to 1575.
Semakovskoye Gas Field
The Semakovskoye Gas Field (Семаковское) is a large natural gas field in northern Russia with over 320 billion m³ of reserves, produced from shore through extended-reach wells since 2022.
Semantic caching
Semantic caching is a caching technique for large language model applications: prompts are compared as embeddings, and similar queries receive a cached response, cutting cost and latency.
Semantic clustering
Semantic clustering is a text-mining method that groups words, sentences, or documents by meaning, converting each into an embedding vector and clustering items whose vectors are close, unlike word-count-based methods.
Semantic entropy
Semantic entropy is an uncertainty measure for large language model output, computed over the meanings of sampled answers rather than their exact wording, proposed in 2023.
Semantic Kernel
Semantic Kernel is Microsoft's open-source, model-agnostic SDK for building and deploying AI agents and multi-agent systems on large language models, released in 2023 and succeeded by Microsoft Agent Framework.
Semantic layer
Semantic layer, also called metrics layer or business layer: a governed abstraction between raw data and BI tools, AI models, and agents defining metrics, dimensions, and relationships once; traces to the BusinessObjects Universe of 1990; the Open Semantic Interchange specification (now Apache Ossie, incubating) was published in 2026.
Semantic network
A semantic network, also known as a semantic net, is a knowledge representation in which concepts are graph nodes and semantic relations are labeled edges.
Semantic parsing
Semantic parsing is the natural language processing task of translating utterances into machine-readable meaning representations, so users can query databases without a formal query language.
Semantic role labeling
Semantic role labeling (SRL) is a natural language processing method that identifies verbs in a sentence and assigns roles such as agent or patient to their arguments.