Wednesday, March 18, 2026
- Videosv5This page collects influential video content about artificial intelligence, machine learning, and deep learning. The first section surveys the YouTube channels that have shaped how people learn AI online.
- Video Classification Modelsv5Video classification models are machine learning systems that assign one or more category labels to a video clip, typically describing the human action depicted.
- Video-MMMUv3Video-MMMU (Video Multi-Modal Multi-disciplinary Understanding, sometimes written VideoMMMU) is a benchmark that measures whether Large Multimodal Models can acquire new knowledge from professional educational…
- Video GPT by VEEDv5Video GPT by VEED (also stylized as VideoGPT by VEED) is an artificial intelligence text-to-video tool developed by the London-based online video editing company VEED.IO.
- Vibe Coding Tips and Tricksv4Vibe coding is the practice of building software by describing what you want in natural language and letting an AI write the code.
- Vibe codingv9Vibe coding is a software development practice in which a programmer describes their intent in plain natural language and relies on a large language model (LLM) to generate the corresponding source code.
- Vector embeddingsv11Vector embeddings are dense numerical representations of objects (text, images, audio, video, code, graphs, or any structured data) that map them into a continuous vector space such that semantic similarity…
- Vector databasev10A vector database is a database that stores data as high-dimensional vectors (numerical embeddings produced by a machine learning model) and retrieves records by similarity rather than exact match
- Variable importancesv4Variable importances, also called feature importances, are scores assigned to each input variable of a predictive model that measure how much that variable contributes to the model's output.
- Vanishing Gradient Problemv9The vanishing gradient problem is a difficulty in training deep neural networks where the gradients used to update the network shrink exponentially as they are propagated backward through the layers, leaving…
- Validation Setv6A validation set (also called a development set or dev set) is a subset of labeled data that is held out from the training set and used to evaluate a model's performance during development
- Validation lossv4Validation loss is the value of a model's loss function measured on a held-out validation set, data the model never sees during weight updates, and it is the primary signal practitioners use to judge how well…
- Validationv4Validation in machine learning is the process of checking how well a trained model performs on data it did not see during training, using a held-out validation set to tune hyperparameters, choose between…
- User matrixv7In collaborative filtering and matrix factorization recommender systems, the user matrix (commonly written U or P) is the matrix of latent-factor vectors for users: each row is one user's embedding in a…
- Upweightingv5Upweighting is the practice of assigning a larger weight to certain training examples (or groups of examples) so they contribute more to the loss function and gradient updates than the rest of the data.
- Uplift Modelingv8Uplift modeling (also called incremental modeling, true lift modeling, or net modeling) is a set of machine learning and statistical techniques that predict the incremental impact of a treatment or action on…
- Unsupervised Machine Learningv7Unsupervised machine learning is a type of machine learning that finds patterns, structures, and relationships in data that has no labels, with no human-provided answer key to learn from.
- Unsupervised learningv6Unsupervised learning is a branch of machine learning in which algorithms identify patterns, structures, and relationships in data without relying on labeled examples or explicit human guidance.
- Unstable Diffusionv4Unstable Diffusion is a Discord community and affiliated commercial platform, operated by the company Equilibrium AI
- Unlabeled examplev5An unlabeled example is a data instance that has one or more features but no label, meaning it carries the inputs a model reads but not the target answer the model is meant to produce.
- Universev4Universe was an open-source software platform that OpenAI released on December 5, 2016 for measuring and training an artificial intelligence agent's general intelligence across, in OpenAI's words, "the world's…
- Universal Speech Modelv6The Universal Speech Model (USM) is a family of large multilingual speech models developed by Google Research that performs automatic speech recognition (ASR) and speech-to-text translation across more than…
- Unidirectional language modelv5A unidirectional language model is a language model that predicts each token using only the tokens that come before it in the sequence (the left context), via causal (autoregressive) masking
- Unidirectionalv7Unidirectional is a property of a sequence model in which the representation or output at each position depends only on inputs from one direction of the sequence
- 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 is no longer drowned out.
- Underfittingv6Underfitting occurs when a machine learning model is too simple to capture the underlying patterns in the data.
- 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 samples from that learned distribution, with no extra…
- 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 model fair by simply not giving it the sensitive or…
- 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), where TP is the number of true positives and FN the…
- 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.
- 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 predicted label is also negative.
- Transformersv16A Transformer is a deep learning architecture, introduced by eight Google researchers in the 2017 paper "Attention Is All You Need", that uses attention as the sole mechanism for modeling relationships between…
- Transfer Learningv11Transfer learning is a family of machine learning methods in which information learned from one source domain or task is used while learning a target domain or task.
- 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.
- Training Setv9A training set is the portion of data used to fit a statistical or machine learning model.
- Training lossv8In machine learning, training loss is the value of the loss function computed on the training data during model training, and it is the exact quantity that the optimization algorithm minimizes at each step.
- Training-Serving Skewv9Training-serving skew is a difference between a machine learning model's performance during training and its performance during serving (production inference).
- 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.
- Towerv6In deep learning, a tower is a self-contained sub-network inside a larger model that encodes one specific input or feature group into an output, usually an embedding
- 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 typically a word, subword piece, or character.
- Tokenv8A token is the basic unit of text that a language model reads and writes: a word, a subword fragment, a single character, or a byte, produced by splitting text during a step called tokenization.
- Timestepv8A timestep is a discrete unit of time progression in a sequential process. The term shows up in many corners of machine learning and applied math, and it does not always mean the same thing.
- Time Series Analysisv11Time series analysis is the statistical study of ordered observations when dependence across time is part of the signal rather than a nuisance to ignore.
- 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.
- The New Stack and Ops for AI (OpenAI Dev Day 2023)v5The New Stack and Ops for AI is a technical breakout session presented by Sherwin Wu and Shyamal Hitesh Anadkat at OpenAI DevDay 2023, held on November 6, 2023, in San Francisco.
- tf.kerasv8tf.keras is the high-level deep learning API built directly into the TensorFlow machine learning framework
- Tf.Examplev6tf.train.Example (commonly written as tf.Example) is a Protocol Buffers message type that TensorFlow uses as its standard on-disk representation for a single training or inference example.
- 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 preceding context.
- Text Classification Modelsv6Text classification models are machine learning systems that assign one or more predefined categorical labels to a span of natural language text, such as positive vs. negative, spam vs. ham
- 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 an input text string
- Text-to-Speech Modelsv5Text-to-speech (TTS) models are machine learning systems that convert written text into spoken audio.
- Text-to-Image Modelsv7Text-to-image models are generative artificial intelligence systems that synthesize a new image from a natural-language description, called a prompt.
- Test Setv11A test set is a collection of examples reserved from model fitting and model selection so that it can evaluate a fixed machine learning model or a fully specified learning procedure.
- Test lossv4Test loss is the value of a loss function computed on a held-out test data set: data that was used neither for training nor for validation or model selection.
- Termsv9Terms is the AI Wiki's top-level glossary, a single alphabetical index that defines and links artificial intelligence vocabulary, machine learning concepts, and AI model, tool, and company names.
- Termination conditionv7A termination condition, also called a stopping criterion, convergence criterion, or halting condition, is a rule that decides when an iterative algorithm should stop running.
- Tensor sizev4The size of a tensor is a description of how big the tensor is, and the term carries two distinct meanings in everyday deep learning.
- Tensor Shapev4A tensor shape is a tuple of integers that describes the number of elements along each dimension (or axis) of a tensor.
- 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.
- TensorFlow Servingv9TensorFlow Serving (often shortened to TF Serving) is Google's open source system for serving machine learning models in production: it loads trained models, exposes them over gRPC and REST APIs, and manages…
- TensorFlow Playgroundv5TensorFlow Playground (also called the Neural Network Playground, titled Deep playground in its source repository, and, in Google's education properties, simply Playground) is a free, interactive…
- TensorFlowv11TensorFlow is an open-source software platform for numerical computation and machine learning.
- TensorBoardv6TensorBoard is the open-source visualization toolkit for TensorFlow, described by Google as "a suite of visualization tools to understand, debug, and optimize TensorFlow programs for ML experimentation." It…
- Tensorv6In machine learning, a tensor is a multi-dimensional array of numbers that serves as the fundamental data structure for representing and manipulating data.
- Temporal datav4Temporal data is data where each observation is tagged with a timestamp, so the order in which observations arrive carries meaning.
- Technology ChatGPT Pluginsv6Technology ChatGPT Plugins were the group of third-party extensions in the ChatGPT Plugins store that focused on technology news, software documentation, repository search, and general developer or…
- Technologyv9Technology is one of the largest application domains for artificial intelligence, spanning enterprise IT operations, cloud computing, cybersecurity, software development, networking, semiconductor…
- Tau2-benchv4τ²-bench (also written Tau2-bench or τ^2-bench) is a benchmark for evaluating conversational AI agents in dual-control environments, where both the agent and a simulated user can call tools to read from and…
- τ-benchv15τ-bench (Tau-bench), short for Tool-Agent-User Interaction Benchmark, is an AI benchmark that evaluates language agents' ability to complete complex tasks through realistic, multi-turn interactions with…
- Target Networkv6A target network is a separate, slowly updated copy of a neural network used in deep reinforcement learning to compute stable learning targets
- Targetv6In supervised learning, the target is the variable that a model learns to predict from input features.
- Tabular Regression Modelsv7Tabular regression models are machine learning systems that predict a continuous numeric target from a vector of tabular features, where rows are samples and columns are heterogeneous attributes (numeric…
- 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 a lookup table, the Q-table
- 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.
- Tabular Classification Modelsv7Tabular classification models predict a discrete label, or a probability distribution over labels, from rows of a table.
- Table Question Answering Modelsv6Table question answering models (TableQA models) are machine learning systems that answer natural language questions over structured tabular data such as spreadsheets, database tables, and HTML tables…
- 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 computation on that attached hardware.
- 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, v4, v5e, v5p, v6e (Trillium), and v7 (Ironwood).
- 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 high-speed inter-chip interconnect (ICI).
- TPU resourcev5A TPU resource is an allocation of Tensor Processing Unit compute, Google's custom machine learning accelerator chips, that you reserve and run as a unit
- TPU Nodev8A TPU node is the legacy Google Cloud architecture for accessing Tensor Processing Unit (TPU) hardware, in which a user's virtual machine (VM) runs application code and communicates with a separate
- TPU Masterv6The TPU master is the control and coordination role in Google's Tensor Processing Unit (TPU) system that drives the actual TPU computation.
- TPU Devicev6A TPU device is a Google-designed application-specific integrated circuit (ASIC), the physical Tensor Processing Unit chip and its host hardware
- TPU Chipv9This article covers the TPU chip and its hardware. For the broader topic, see Tensor Processing Unit (TPU).
- TPU Podv6A TPU Pod is a single Google supercomputer built from many Tensor Processing Unit (TPU) chips wired directly to each other by a high-speed Inter-Chip Interconnect (ICI) fabric arranged as a 2D or 3D torus, so…
- Tensor Processing Unit (TPU)v11A Tensor Processing Unit (TPU) is a family of custom application-specific integrated circuits developed by Google to accelerate machine-learning computation.
- System promptv6A system prompt is a special set of instructions, guidelines, persona definitions, and contextual information given to a large language model (LLM) before any user input
- Synthetic Featurev6A synthetic feature (also called a constructed feature or derived feature) is a variable created by transforming, combining, or otherwise manipulating one or more existing features in a dataset, rather than…
- Supervised Machine Learningv10Supervised machine learning is a branch of machine learning in which a model learns a mapping from inputs to outputs by training on labeled examples, where every input (a feature vector) is paired with the…
- Supervised Learningv9Supervised learning is a machine learning paradigm in which a model is fitted to examples that pair an input with an observed target.
- Supervised fine-tuningv7Supervised fine-tuning (SFT) is supervised training applied to a model that has already been trained.
- Summaryv4In TensorFlow, a summary is a piece of data written to disk during training so that it can later be visualized in TensorBoard. The tf.summary module is the API used to record those values.
- Summarization Modelsv5Summarization models are natural language processing systems that condense a source document, set of documents, or dialogue into a shorter version that preserves the most important information.
- 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 compute cost, add regularization, or rebalance a…
- 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 data and controls the capacity of the hypothesis…
- 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 one position at a time and visits every location…
- Stochastic Gradient Descent (SGD)v10Stochastic gradient descent (SGD) is a first-order optimization method that updates parameters using a gradient estimate computed from a randomly selected example or subset of examples.
- Step sizev6In machine learning, the step size…
- Stepv5In machine learning, a step is one discrete update in an iterative process, most often a single update of a model's parameters computed from one mini-batch of training data (also called a training step…
- Sparse Representationv7Sparse representation is a data encoding strategy in which most values in a vector, matrix, or tensor are zero (or near zero), with only a small fraction of elements carrying non-zero values.
