Thursday, July 23, 2026
- True positivev8A true positive (TP) is a prediction that is correctly positive: the model predicts the positive class and the true label is also positive.[^1][^3][^17] It is...
- Training-Serving Skewv9Training-serving skew is a difference between a machine learning model's performance during training and its performance during serving (production inference)....
- Training lossv8See also: Loss function, Validation loss, Learning curve In machine learning, training loss is the value of the loss function computed on the training data...
- Undersamplingv6Undersampling is a class imbalance handling technique in machine learning that removes examples from the majority class of a training set so the minority class...
- Universal Speech Modelv6See also: Papers The Universal Speech Model (USM) is a family of large multilingual speech models developed by Google Research that performs automatic speech...
- Unawareness (Fairness Through Unawareness)v4Unawareness to a sensitive attribute, more commonly called fairness through unawareness (FTU), is a machine learning fairness approach that tries to make a...
- Unidirectionalv7See also: Machine learning terms Unidirectional is a property of a sequence model in which the representation or output at each position depends only on inputs...
- Unidirectional language modelv5See also: Machine learning terms A unidirectional language model is a language model that predicts each token using only the tokens that come before it in the...
- Unconditional Image Generation Modelsv5Unconditional image generation models are generative neural networks that learn the marginal distribution p(x) of a set of training images and produce new...
- Universev4Universe was an open-source software platform that OpenAI released on December 5, 2016 for measuring and training an artificial intelligence agent's general...
- Transformersv13> Note: This article is about the neural network architecture introduced in 2017. For the open-source Python library by Hugging Face, see Hugging Face...
- Unlabeled examplev5See also: Machine learning terms An unlabeled example is a data instance that has one or more features but no label, meaning it carries the inputs a model...
- Underfittingv6Underfitting occurs when a machine learning model is too simple to capture the underlying patterns in the data.[1][3] An underfit model performs poorly not...
- Unsupervised learningv6Unsupervised learning is a branch of machine learning in which algorithms identify patterns, structures, and relationships in data without relying on labeled...
- True negativev9A true negative (TN) is a case that a binary classification model correctly predicts as belonging to the negative class: the true label is negative and the...
- Training Setv8See also: Machine learning terms A training set is the portion of a dataset that a machine learning model learns from: the labeled examples a model processes...
- Transfer Learningv10See also: Machine learning terms Transfer learning is a machine learning technique that reuses knowledge a model has gained on one task or domain to improve...
- Trajectory (Reinforcement Learning)v7A trajectory in reinforcement learning is a sequence of states, actions, and rewards that an agent experiences while interacting with an environment. Formally...
- True positive rate (TPR)v5The true positive rate (TPR) is the proportion of actual positive cases that a classifier correctly identifies as positive, computed as TPR = TP / (TP + FN),...
- Unstable Diffusionv4Unstable Diffusion is a Discord community and affiliated commercial platform, operated by the company Equilibrium AI, dedicated to artificial intelligence (AI)...
- Towerv6See also: two-tower model, dual encoder, cross-encoder, contrastive learning, embedding, recommendation system, information retrieval Not to be confused with...
- Test lossv4See also: Machine learning terms Test loss is the value of a loss function computed on a held-out test data set: data that was used neither for training nor...
- Tensor sizev4See also: tensor, shape, tensor rank, dtype The size of a tensor is a description of how big the tensor is, and the term carries two distinct meanings in...
- Text Generation Modelsv6Text generation models are language models trained to produce coherent natural-language text by predicting tokens one at a time, each conditioned on the...
- Threshold (for decision trees)v5In a decision tree, a threshold is the cut point used in an internal node's split test that decides which child subtree a sample is routed to. For a numerical...
- Text2Text Generation Modelsv5Text-to-text (text2text) generation models are a family of neural network systems that frame many natural language processing tasks as a single problem: given...
- Termination conditionv7See also: Machine learning terms A termination condition, also called a stopping criterion, convergence criterion, or halting condition, is a rule that decides...
- Time Series Analysisv10See also: Machine learning terms Time series analysis is the statistical and computational study of data points indexed in chronological order, with the goal...
- Termsv7Terms is the AI Wiki's top-level glossary, a single alphabetical index that defines and links artificial intelligence vocabulary, machine learning concepts,...
- Trainingv6Training in machine learning is the process of fitting a model's parameters to data so that the model can make accurate predictions or generate useful outputs....
- Text-to-Image Modelsv7See also: Multimodal Models and Tasks Text-to-image models are generative artificial intelligence systems that synthesize a new image from a natural-language...
- Tokenv8See also: Machine learning terms, Tokenization, Byte pair encoding A token is the basic unit of text that a language model reads and writes: a word, a subword...
- Token Classification Modelsv5Token classification models are natural language processing systems that assign a discrete label to every token in an input sequence, where a token is...
- Text Classification Modelsv6See also: Natural Language Processing Models and Tasks Text classification models are machine learning systems that assign one or more predefined categorical...
- Test Setv10A test set is a portion of data held back from model development and used only once, after all training and tuning is complete, to give an unbiased estimate of...
- tf.kerasv8tf.keras is the high-level deep learning API built directly into the TensorFlow machine learning framework, and it has been TensorFlow's official and...
- The New Stack and Ops for AI (OpenAI Dev Day 2023)v5The New Stack and Ops for AI Type OpenAI DevDay 2023 Organization OpenAI (YouTube) Presenters A framework for navigating the unique considerations of...
- Timestepv8See also: Machine learning terms A timestep is a discrete unit of time progression in a sequential process. The term shows up in many corners of machine...
- Text-to-Speech Modelsv5Text-to-speech (TTS) models are machine learning systems that convert written text into spoken audio. The modern lineage runs from DeepMind's WaveNet (2016),...
- TPU Workerv6A TPU worker is a virtual machine (VM) running Linux that has direct access to one or more Tensor Processing Unit (TPU) chips and executes the actual TPU...
- Tabular modelsv4Tabular models are machine learning systems that learn from data arranged in tables, where each row is a sample and each column is a feature. The defining...
- Targetv6See also: Machine learning terms In supervised learning, the target is the variable that a model learns to predict from input features. It is the answer side...
- Tabular Classification Modelsv6Part of the Tabular Models hub. See also the sibling survey Tabular Regression Models. Tabular classification models are machine learning systems that predict...
- TensorFlowv9TensorFlow is a free, open-source software library for machine learning and numerical computation, developed by the Google Brain team and first released on...
- τ-benchv13τ-bench (Tau-bench), short for Tool-Agent-User Interaction Benchmark, is an AI benchmark that evaluates language agents' ability to complete complex tasks...
- Tabular Regression Modelsv7See also: Tabular Models and Tasks Tabular regression models are machine learning systems that predict a continuous numeric target from a vector of tabular...
- TensorBoardv6See also: Machine learning terms, TensorFlow, Data Visualization TensorBoard is the open-source visualization toolkit for TensorFlow, described by Google as "a...
- Tensor Shapev4A tensor shape is a tuple of integers that describes the number of elements along each dimension (or axis) of a tensor. For a tensor of rank r, the shape is...
- Tau2-benchv3τ²-bench: Evaluating Conversational Agents in a Dual-Control Environment Abbreviation 2025-06-12 (v0.1.0) Latest version arXiv:2506.07982 (2025-06-09) ...
- Technology ChatGPT Pluginsv6See also: ChatGPT Plugins, ChatGPT Plugin Categories and Technology Technology ChatGPT Plugins were the group of third-party extensions in the ChatGPT Plugins...
- Temporal datav4See also: Machine learning terms Temporal data is data where each observation is tagged with a timestamp, so the order in which observations arrive carries...
- Tabular Q-Learningv5Tabular Q-learning is the classic form of Q-learning, a model-free reinforcement learning algorithm that stores the action-value function Q(s, a) explicitly in...
- Tensorv6See also: Machine learning terms In machine learning, a tensor is a multi-dimensional array of numbers that serves as the fundamental data structure for...
- Tensor Rankv6The rank of a tensor, also referred to as its order or degree, is the number of dimensions (axes or indices) needed to describe the tensor. A scalar has rank...
- TensorFlow Playgroundv5See also: Machine learning terms, Neural network, Deep learning TensorFlow Playground (also called the Neural Network Playground, titled Deep playground in its...
- Technologyv7Technology is one of the largest application domains for artificial intelligence, spanning enterprise IT operations, cloud computing, cybersecurity, software...
- Target Networkv6A target network is a separate, slowly updated copy of a neural network used in deep reinforcement learning to compute stable learning targets, decoupling the...
- TPU Devicev6A TPU device is a Google-designed application-specific integrated circuit (ASIC), the physical Tensor Processing Unit chip and its host hardware, built to...
- Subsamplingv7Subsampling is the practice of drawing a smaller subset from a larger collection of data points, training examples, features, or signal values, in order to cut...
- TPU resourcev5See also: Machine learning terms, Tensor Processing Unit (TPU) A TPU resource is an allocation of Tensor Processing Unit compute, Google's custom machine...
- Tensor Processing Unit (TPU)v8See also: Machine learning terms, GPU, Deep learning, Edge TPU, AI chip A Tensor Processing Unit (TPU) is a custom application-specific integrated circuit...
- Summarization Modelsv5Summarization models are natural language processing systems that condense a source document, set of documents, or dialogue into a shorter version that...
- Structural risk minimization (SRM)v7Structural risk minimization (SRM) is an inductive principle in statistical learning theory for selecting a learned model that simultaneously fits the training...
- Supervised Machine Learningv10See also: Machine learning terms Supervised machine learning is a branch of machine learning in which a model learns a mapping from inputs to outputs by...
- Stochastic Gradient Descent (SGD)v9See also: Machine learning terms Stochastic gradient descent (SGD) is an iterative optimization algorithm that updates model parameters using the gradient of...
- Supervised Learningv8See also: Machine learning, Unsupervised learning, Reinforcement learning Supervised learning is a type of machine learning in which an algorithm learns from...
- Supervised fine-tuningv6Supervised fine-tuning (SFT) is the process of further training a pre-trained large language model (LLM) on a smaller, labeled dataset of input-output pairs so...
- Summaryv4See also: TensorFlow, TensorBoard, Machine learning terms In TensorFlow, a summary is a piece of data written to disk during training so that it can later be...
- TPU Typev5The types of TPU (Tensor Processing Unit) are the successive generations of custom machine-learning accelerator that Google has built since 2015: v1, v2, v3,...
- TPU Slicev6A TPU slice is a collection of Tensor Processing Unit (TPU) chips that all sit inside the same Google Cloud TPU Pod and are connected to one another by a...
- Synthetic Featurev6A synthetic feature (also called a constructed feature or derived feature) is a variable created by transforming, combining, or otherwise manipulating one or...
- TPU Chipv9This article covers the TPU chip and its hardware. For the broader topic, see Tensor Processing Unit (TPU). The Tensor Processing Unit (TPU) is a custom...
- TPU Masterv6The TPU master is the control and coordination role in Google's Tensor Processing Unit (TPU) system that drives the actual TPU computation. In the TensorFlow...
- System promptv6See also: Prompt, User prompt, and Prompt engineering A system prompt is a special set of instructions, guidelines, persona definitions, and contextual...
- TPU Podv6See also: Tensor Processing Unit (TPU), Cloud TPU, Data parallelism, Model parallelism, Distributed training A TPU Pod is a single Google supercomputer built...
- Stridev7Stride is the step size by which a filter (or pooling window) moves across the input in a convolutional neural network (CNN): a stride of 1 shifts the filter...
- SimpleBenchv3--- SimpleBench: The Text Benchmark in which Unspecialized Human Performance Exceeds that of Current Frontier Models Description July 24, 2024 Public...
- Social Mediav5See also: Social Media ChatGPT Plugins Artificial intelligence shapes nearly every part of modern social media, from the order of posts in a feed to the...
- SimpleQAv6SimpleQA is a factuality benchmark released by OpenAI on October 30, 2024 that measures whether large language models can answer short, fact-seeking questions...
- Softmaxv10See also: Machine learning terms The softmax function is a mathematical function that converts a vector of real numbers, often called logits, into a...
- Social Media ChatGPT Pluginsv4See also: ChatGPT Plugins, ChatGPT Plugin Categories and Social Media Social Media ChatGPT Plugins were third-party extensions for ChatGPT that connected the...
- Sigmoid Functionv12See also: Machine learning terms The sigmoid function is a mathematical function that maps any real number to a value between 0 and 1 using the formula ,...
- Software Development ChatGPT Pluginsv4See also: ChatGPT Plugins, ChatGPT Plugin Categories and Software Development Software Development ChatGPT Plugins were a now-deprecated category of ChatGPT...
- SmolVLAv5See also: Terms and artificial intelligence terms SmolVLA (Small Vision-Language-Action) is a compact, open-source vision-language-action model (VLA) for...
- Software Developmentv4See also: Software Development ChatGPT Plugins AI in software development is the use of large language models and other machine learning systems to write,...
- Softwarev3See also: Software ChatGPT Plugins The phrase AI in software, or AI-powered software products, covers the integration of artificial intelligence, especially...
- Stepv5See also: Machine learning terms In machine learning, a step is one discrete update in an iterative process, most often a single update of a model's parameters...
- Spacev4See also: Space ChatGPT Plugins Artificial intelligence in space refers to the use of machine learning, deep learning, autonomous planning systems, and other...
- Size invariancev6See also: Machine learning terms Size invariance, also called scale invariance, is the property of a model, feature, or algorithm that produces the same output...
- Space ChatGPT Pluginsv4Space ChatGPT plugins were a group of third-party tools that extended ChatGPT with the ability to fetch astronomical imagery, track the International Space...
- Step sizev6See also: learning rate, parameter update, Adam, SGD In machine learning, the step size (also called the learning rate, usually written as the Greek letter ...
- Similarity Measurev8See also: Machine learning, Clustering, Information retrieval A similarity measure (also called a similarity function or similarity metric) is a real-valued...
- Software ChatGPT Pluginsv5See also: ChatGPT Plugins, ChatGPT Plugin Categories and Software Software ChatGPT Plugins were a broad category of third-party extensions inside ChatGPT that...
- Sparse Representationv7See also: Machine learning terms Sparse representation is a data encoding strategy in which most values in a vector, matrix, or tensor are zero (or near zero),...
- Sparse Featurev7A sparse feature is a feature in machine learning whose values are predominantly zero or empty across a dataset. Google's Machine Learning Crash Course defines...
- Selection Biasv8Selection bias is a systematic error that occurs when the data used for analysis, training, or evaluation does not accurately represent the population or...
- Servingv4See also: Inference, Model, Training, MLOps In machine learning, serving (also called model serving or inference serving) is the process of deploying a trained...
- Sentence-transformers/all-mpnet-base-v2 modelv5Hugging Face sentence-transformers/all-mpnet-base-v2 Name all-mpnet-base-v2 User / Organization sentence-transformers Type Natural Language Processing Task...
- Sentence-transformers/all-MiniLM-L6-v2 modelv6Sentence-transformers/all-MiniLM-L6-v2 model Hugging Face sentence-transformers/all-MiniLM-L6-v2 Name all-MiniLM-L6-v2 User / Organization...
- Self-Improvement ChatGPT Pluginsv5Self-Improvement ChatGPT Plugins were third party tools available inside the ChatGPT plugins marketplace that focused on personal growth, habit formation,...
