Machine Learning

TensorBoard

TensorBoard is the open-source visualization toolkit for TensorFlow, described by Google as "a suite of visualization tools to understand, debug, and optimize...

Data ScienceDeveloper Tools

TensorFlow

TensorFlow is a free, open-source software library for machine learning and numerical computation, developed by the Google Brain team and first released on...

AI Tools & ProductsDeep Learning

TensorFlow Decision Forests (TF-DF)

TensorFlow Decision Forests (often abbreviated TF-DF) is an open-source Google library for training, serving, and interpreting decision-forest models such as...

Developer ToolsGoogle

TensorRT

TensorRT is NVIDIA's software development kit (SDK) for high-performance deep learning inference on NVIDIA GPUs. It takes trained neural networks and optimizes...

AI HardwareAI Tools & Products

Termination condition

See also: Machine learning terms A termination condition, also called a stopping criterion, convergence criterion, or halting condition, is a rule that decides...

Training & Optimization

Test Set

A 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...

Model Evaluation

Test loss

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 for validation or model selection....

Test-Time Training (TTT)

Test-Time Training (TTT) is a family of machine learning techniques in which a model updates a subset of its own parameters at inference time, optimizing a...

AI InferenceTraining & Optimization

Test-time compute

Test-time compute (also called inference-time compute scaling or test-time scaling) is the practice of allocating additional computation while a large language...

Artificial IntelligenceLarge Language Models

Text summarization

Text summarization is the natural language processing (NLP) task of automatically producing a shorter version of one or more documents that preserves the most...

Deep LearningNatural Language Processing

The Pile (dataset)

The Pile is an 825.18 GiB (approximately 886 GB) English text corpus designed for training large language models, assembled from 22 diverse, high-quality...

Data & DatasetsNatural Language Processing

The Stack v2

The Stack v2 is a large open dataset of source code released by BigCode in February 2024 as the training dataset behind the StarCoder2 family of code models....

Data & Datasets

Threshold (for decision trees)

In 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...

TikTok

TikTok is a short-form video app owned by the Chinese technology company ByteDance, best known in artificial intelligence circles as the most widely studied...

AI Policy & RegulationAI Tools & Products

Time Series Analysis

Time series analysis is the statistical and computational study of data points indexed in chronological order, with the goal of extracting patterns such as...

Data ScienceStatistics

Timestep

See 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...

Token

A 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...

Deep LearningNatural Language Processing

Tokenization

Tokenization is the process of breaking text into smaller units called tokens, which serve as the fundamental input to natural language processing (NLP)...

Large Language ModelsNatural Language Processing

Top-p and top-k sampling

Top-p sampling, also called nucleus sampling, is a text-generation decoding method for large language models (LLMs) that, at each step, samples the next token...

Large Language ModelsNatural Language Processing

Top-p sampling

Top-p sampling, also called nucleus sampling, is a stochastic decoding method for text generation in which the model samples from the smallest possible set of...

Large Language ModelsNatural Language Processing

TopK SAE

A TopK SAE (TopK sparse autoencoder) is a variant of sparse autoencoder that enforces sparsity by keeping only the K largest latent pre-activations for each...

AI Safety

Topic model

A topic model is a statistical model that discovers the abstract "topics" hidden in a collection of documents, where each document is represented as a mixture...

Natural Language ProcessingStatistics

Tower

See also: two-tower model, dual encoder, cross-encoder, contrastive learning, embedding, recommendation system, information retrieval Not to be confused with...

Information RetrievalModel Architecture

Training

Training 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....

Deep Learning

Training Set

A training set is the portion of a dataset that a machine learning model learns from: the labeled examples a model processes during training to adjust its...

Data & Datasets

Training run

A training run is a single, deliberate instance of training a neural network from scratch (or from a prior checkpoint) on a specified dataset, with a fixed...

Training & Optimization

Training-Serving Skew

Training-serving skew is a difference between a machine learning model's performance during training and its performance during serving (production inference)....

Data & DatasetsMLOps

Trajectory (Reinforcement Learning)

A trajectory in reinforcement learning is a sequence of states, actions, and rewards that an agent experiences while interacting with an environment. Formally...

Reinforcement Learning

Transfer Learning

Transfer learning is a machine learning technique that reuses knowledge a model has gained on one task or domain to improve performance on a different but...

Deep Learning

Trigram

See also: N-gram, Bigram, Language model A trigram is a contiguous sequence of three items (most often three words) drawn from a sample of text or speech, and...

Natural Language Processing

True negative

A 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...

Model EvaluationStatistics

True positive

A 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...

Model EvaluationStatistics

True positive rate (TPR)

The true positive rate (TPR) is the proportion of actual positive cases that a classifier correctly identifies as positive, computed as TPR = TP / (TP + FN),...

Model Evaluation

TruthfulQA

TruthfulQA is a benchmark designed to measure whether large language models (LLMs) generate truthful answers to questions. Created by Stephanie Lin, Jacob...

AI BenchmarksAI Safety

Two-Tower Model

The two-tower model, also known as the dual encoder, bi-encoder, or Siamese network for retrieval, is a neural network architecture that encodes a query and a...

Information RetrievalNeural Networks

U-Net

U-Net is a convolutional neural network architecture designed for biomedical image segmentation. It was introduced by Olaf Ronneberger, Philipp Fischer, and...

Computer VisionDeep Learning

UMAP (Uniform Manifold Approximation and Projection)

UMAP (Uniform Manifold Approximation and Projection) is a nonlinear dimensionality reduction technique that compresses high-dimensional data into a...

Data Science

Unawareness (Fairness Through Unawareness)

Unawareness to a sensitive attribute, more commonly called fairness through unawareness (FTU), is a machine learning fairness approach that tries to make a...

AI Ethics

Underfitting

Underfitting 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...

Undersampling

Undersampling is a class imbalance handling technique in machine learning that removes examples from the majority class of a training set so the minority class...

Statistics

Universal Approximation Theorem

The universal approximation theorem states that a feedforward neural network with a single hidden layer of finite width and a suitable nonlinear activation...

Universal Manipulation Interface

Universal Manipulation Interface (UMI) is an open-source system for collecting robot manipulation training data with a handheld, camera-equipped gripper...

Robotics

Unlabeled example

An 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...

Unsupervised Machine Learning

Unsupervised machine learning is a type of machine learning that finds patterns, structures, and relationships in data that has no labels, with no...

Unsupervised learning

Unsupervised learning is a branch of machine learning in which algorithms identify patterns, structures, and relationships in data without relying on labeled...

Artificial IntelligenceData Science

Uplift Modeling

Uplift modeling (also called incremental modeling, true lift modeling, or net modeling) is a set of machine learning and statistical techniques that predict...

Data ScienceStatistics

Upweighting

See also: Machine learning terms Upweighting is the practice of assigning a larger weight to certain training examples (or groups of examples) so they...

User matrix

See also: Machine learning terms In collaborative filtering and matrix factorization recommender systems, the user matrix (commonly written U or P) is the...

V-JEPA

V-JEPA (Video Joint Embedding Predictive Architecture) is a self-supervised video model from Meta AI that learns by predicting masked regions of a video in an...

AI ModelsComputer Vision

VAPO (Value-based Augmented PPO)

VAPO (Value-based Augmented Proximal Policy Optimization) is a reinforcement learning framework for training large language models on long chain-of-thought...

Reinforcement Learning

Validation

Validation 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...

Validation Set

A 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...

Model Evaluation

Validation loss

Validation 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...

Vanishing Gradient Problem

See also: Machine learning terms The vanishing gradient problem is a difficulty in training deep neural networks where the gradients used to update the network...

Deep LearningNeural Networks

Variable importances

Variable importances, also called feature importances, are scores assigned to each input variable of a predictive model that measure how much that variable...

Interpretability

Variational Inference

Variational inference (VI), also called variational Bayes (VB), is a method in machine learning and statistics that approximates an intractable posterior...

Statistics

Vector database

A vector database is a database that stores data as high-dimensional vectors (numerical embeddings produced by a machine learning model) and retrieves records...

AI InfrastructureDeveloper Tools

Wasserstein Loss

Wasserstein loss is a loss function for training generative models that measures the distance between two probability distributions as the Wasserstein-1...

Generative AIMathematics

Wav2Vec 2.0

Wav2Vec 2.0 is a self-supervised learning framework for speech representation, developed by the Facebook AI Research (FAIR) group at Meta and introduced in...

Speech & Audio AI

Weak supervision

Weak supervision is a machine learning paradigm in which models are trained from noisy, limited, imprecise, or programmatically generated labels rather than...

Data & Datasets