Machine learning terms

RawGraph

Machine learning terms are the vocabulary used to describe data, models, training procedures, evaluation methods, and deployed behavior. This page is a curated glossary of terms that recur across research papers, software documentation, and applied practice. It is a companion to the broader Machine Learning article, not a second survey of the field. Readers who need an exhaustive index can use Machine learning terms/All; readers who need a tutorial or the history of a method should follow the linked concept article.

The vocabulary is not controlled by one universal glossary. International terminology standards, public-sector glossaries, textbooks, and framework documentation overlap, but they serve different audiences and sometimes draw boundaries differently.[1][2][3] A model, for example, may mean a fitted mathematical function, a set of learned parameters, or a packaged artifact. Bias can refer to a statistical error component, a parameter in a neural network, or a harmful sociotechnical tendency. Token, state, fairness, and explainability likewise depend on the task and discipline. The definitions below state the intended context and preserve important qualifications rather than forcing all uses into one meaning.

Most entries describe concepts, not products. A term may have a dedicated AI Wiki page even when its definition here is intentionally short. Classification metrics assume that the positive class and any averaging rule have been specified. Probabilistic metrics depend on the evaluation population and data-generating conditions. Reinforcement-learning entries distinguish an environment's state from the observation available to an agent, and an immediate reward from the return optimized over time. Fairness criteria describe mathematical constraints, not complete judgments about legality or justice. These conventions make the glossary useful as a navigation aid while keeping the separate specialist glossaries and full articles responsible for deeper treatment.

Scope and conventions

This glossary favors durable concepts over changing library interfaces, cloud product names, or model rosters. A definition describes common technical usage unless it explicitly identifies a narrower statistical, legal, or reinforcement-learning meaning. Symbols and formulas are omitted where ordinary language is sufficient; the linked pages provide derivations and implementation details.

ConventionHow to read an entry
Classification metricsThe positive class, decision threshold, sample weighting, and multiclass or multilabel averaging rule must be specified before two reported values are comparable.[7]
ProbabilitiesA score interpreted as a probability should be checked for calibration on a relevant evaluation population, not assumed to be calibrated because it lies between zero and one.[8]
Data splitsTraining data fit parameters, validation data support choices such as hyperparameters, and a final test set estimates performance only while it remains isolated from those choices.[6][9]
FairnessGroup metrics formalize different and sometimes incompatible criteria. They do not by themselves determine whether a system is fair, lawful, or appropriate for a use.[14][15]
Reinforcement learningReward is an immediate signal, return aggregates future rewards, state is a property of the process model, and an observation may reveal only part of that state.[10]
Language modelsToken counts and perplexity depend on tokenization. Comparisons require the same data, units, and evaluation convention.[12]

Topic guides

The focused glossaries organize specialized vocabulary without duplicating every definition here.

Topic guideCoverage
FundamentalsData, examples, features, labels, training, optimization, generalization, and basic evaluation
Natural language processingTokens, language models, sequence tasks, embeddings, generation, and language evaluation
FairnessGroup criteria, bias analysis, sensitive attributes, and mitigation vocabulary
Decision forestsTrees, bagging, random forests, boosting, splits, and feature importance
Reinforcement learningAgents, environments, policies, value functions, rewards, and sequential decisions
Computer visionImages, convolutions, detection, segmentation, bounding boxes, and overlap measures
Sequence modelsRecurrent networks, attention, transformers, and ordered data
ClusteringUnsupervised grouping, centroids, similarity, and hierarchical methods
Recommendation systemsCandidate generation, ranking, collaborative filtering, and matrix factorization
TensorFlowFramework-specific tensors, graphs, layers, training, and deployment terms
Google CloudProduct-specific infrastructure and managed machine-learning vocabulary

Core glossary

A-C

TermDefinition
AccuracyThe proportion of evaluated predictions that match their reference labels. It can conceal poor performance on a rare or high-cost class, so the class distribution and complementary metrics matter.[7]
ActionA choice available to an agent. In a reinforcement-learning model, an action can affect the next state, the reward, or both according to the environment's dynamics.[10]
Activation functionA function applied to a unit's pre-activation, often to introduce nonlinearity. Different choices also affect gradient flow, output range, and optimization behavior.[5]
AgentThe decision-making entity in a reinforcement-learning formulation. It receives observations or states, selects actions under a policy, and experiences consequences supplied by an environment.[10]
AttentionA mechanism that forms context-dependent combinations of value representations using weights derived from queries and keys. Attention can be used inside recurrent, convolutional, or transformer systems.[5][11]
AUCUsually the area under a receiver operating characteristic curve. For binary scores it summarizes ranking across thresholds; its probabilistic ranking interpretation depends on conventions for direction and tied scores.[7]
AutoencoderA model trained to encode an input into a representation and decode it toward a reconstruction. An ordinary autoencoder is not automatically a probabilistic generative model.[5]
BackpropagationAn efficient application of the chain rule that propagates derivatives backward through a computational graph. It computes gradients; a separate optimizer decides how parameters change.[5]
BaggingAn ensemble procedure that fits learners to resampled training data and aggregates their predictions. Bootstrap aggregation can reduce variance when the component learners are sufficiently diverse.[4]
BatchA collection of examples processed together for one forward evaluation or training step. A batch may be the entire dataset or a subset of it.[3][5]
Batch normalizationA layer that standardizes selected activations using batch statistics during training, then applies learned scale and offset parameters. Inference commonly uses stored estimates rather than the current batch.[5]
Batch sizeThe number of examples in a batch. It influences memory use, the noise of a gradient estimate, throughput, and sometimes optimization behavior.[3][5]
Bellman equationA recursive relation that expresses a value function through expected immediate reward and the value of successor states or state-action pairs.[10]
Bias-variance tradeoffA way to analyze prediction error in which overly restrictive models can have high systematic error while highly flexible fitted models can vary strongly across training samples. It is not a universal two-number diagnosis for every learning problem.[4]
Binary classificationA classification problem whose target has two classes. Metrics still require an explicit choice of which class is treated as positive.[7]
BoostingA family of ensemble methods that builds learners sequentially so later stages address shortcomings of the current ensemble. Reweighting misclassified examples is one form, not the definition of all boosting.[4]
Bounding boxA rectangular region used to localize an object or area of interest in an image. Coordinate conventions and whether edges are inclusive must be specified when boxes are exchanged or scored.[3]
CalibrationAgreement between predicted probabilities and observed frequencies in a defined population. For example, among cases assigned probability near 0.8, a calibrated binary predictor is positive about 80 percent of the time.[8]
ClassOne of the discrete target categories in a classification task. A class is a semantic or operational category, while its stored label may be a number or string.[3]
ClassificationSupervised prediction of discrete labels or label sets. Binary, multiclass, multilabel, and ordinal tasks require different output and evaluation conventions.[4][7]
ClusteringUnsupervised organization of examples into groups according to a chosen representation, similarity measure, and algorithm. A cluster is therefore method-dependent rather than an automatically discovered natural category.[4]
Collaborative filteringRecommendation from patterns of interactions among users and items, rather than only from item attributes. Sparse feedback and unseen users or items create characteristic cold-start limitations.[3]
Computer visionThe study and construction of systems that extract, predict, or generate information involving images or video. Tasks include classification, detection, segmentation, tracking, and generation.[3][5]
Confusion matrixA table whose rows and columns cross reference labels with predicted labels. Its orientation must be stated because software packages differ over which axis represents truth.[7]
ConvolutionAn operation that combines a local kernel with an input across positions while sharing parameters. Deep-learning libraries often implement cross-correlation while retaining the conventional name convolution.[5]
Convolutional neural networkA neural network that uses convolutional layers to exploit local structure and parameter sharing. Convolutional networks are common in vision but also apply to signals, sequences, and grids.[5]
Cross-entropyThe expected negative log probability that one distribution assigns to outcomes drawn from a target distribution. With one-hot classification targets, it becomes the negative log probability assigned to the reference class.[5]
Cross-validationA resampling procedure that rotates observations through training and validation folds to estimate or compare models. Preprocessing and model selection must occur inside each training fold to avoid leakage.[6][9]

D-F

TermDefinition
Data augmentationGeneration of additional training examples by applying label-preserving or target-adjusting transformations to existing data. Whether a transformation is valid depends on the task, such as rotation for some images but not all.[3][5]
Data leakageUse during model construction of information that would not legitimately be available when predictions are made. Leakage usually produces an overly optimistic evaluation and can occur through preprocessing, target proxies, time, or split contamination.[9]
DatasetA defined collection of examples and associated metadata used for training, validation, testing, or analysis. Its sampling process, provenance, schema, and intended use are part of its meaning.[3]
Decision boundaryThe set of input points at which a classifier changes its predicted class or decision. The boundary depends on the representation, model, parameters, and decision rule.[3]
Decision treeA model that routes an example through successive feature-based splits to a leaf prediction. Trees can be used for classification or regression and are often components of ensembles.[4]
Deep learningMachine learning based on layered representations whose intermediate features are learned from data. Depth is relative to the architecture and problem; there is no universal minimum hidden-layer count.[5]
Deep neural networkA neural network with multiple successive representation-learning stages. The word deep describes architectural composition, not a fixed threshold of exactly two or any other number of hidden layers.[5]
Deep Q-networkA Q-learning system that approximates action values with a deep neural network. The influential DQN design combined this approximation with experience replay and a separately updated target network.[10]
Demographic parityA group-fairness criterion under which the rate of a selected prediction or decision is equal across specified groups. It does not condition on the reference outcome and may conflict with other criteria.[14][15]
Diffusion modelA generative model trained around a gradual noising process and a learned reverse or denoising process. Sampling typically begins from noise and follows repeated learned transitions toward a data example.[18]
Dimensionality reductionTransformation of data into fewer coordinates while attempting to preserve selected structure, information, or predictive utility. Different methods preserve different properties.[4]
DiscriminatorIn a generative adversarial network, the model trained to distinguish samples from the data distribution from samples produced by the generator.[16]
Disparate impactDisproportionately adverse effects on a protected group from an apparently neutral practice. It has jurisdiction-specific legal meanings, so a statistical disparity alone is not a complete legal determination.[15]
Distribution shiftA change between the data distribution used to build or evaluate a model and the distribution encountered later. The shift may affect inputs, targets, their relationship, or the surrounding decision process.[3]
DropoutA training method that randomly omits selected units or connections during updates. Inference uses a deterministic full network under a scaling convention that accounts for the training-time omissions.[5]
Early stoppingStopping optimization according to performance on held-out validation data rather than continuing until training loss is minimized. Repeated choices based on the same validation set can themselves overfit it.[5][6]
EmbeddingA vector representation assigned to an item, token, category, or larger object so that a model can operate on it. The geometry is learned or constructed for a task and does not have one context-free semantic interpretation.[3][12]
EnsembleA predictor formed by combining outputs from multiple fitted models. Averaging, voting, stacking, bagging, and boosting create ensembles with different assumptions and failure modes.[4]
EnvironmentEverything in a reinforcement-learning formulation outside the agent that receives actions and produces subsequent states or observations and rewards.[10]
EpochOne traversal of the designated training examples, under a stated sampling convention. With resampling, streaming data, or distributed training, implementations may define an epoch operationally rather than as one unique view of every example.[3]
Equality of opportunityThe one-sided equalized-odds criterion proposed for supervised learning, usually requiring equal true-positive rates across protected groups for the favorable reference outcome.[14]
Equalized oddsA group-fairness criterion requiring prediction to be independent of the protected group conditional on the reference outcome. In binary classification this corresponds to equal true-positive and false-positive rates across groups.[14]
ExampleOne instance presented to or evaluated by a learning procedure. It contains input features and, in supervised settings, may also contain one or more targets.[3]
ExplainabilityThe extent to which a system or supporting method can provide information people can use to understand a result or behavior. A plausible explanation is not automatically a faithful account of the model's computation.[2]
Exploding gradientA training failure in which derivatives grow to very large magnitudes as they propagate through a computation, causing unstable parameter updates or numerical overflow.[5]
F1 scoreThe harmonic mean of precision and recall for a specified positive class. It ignores true negatives and does not encode all application costs, probability calibration, or threshold preferences.[7]
Fairness metricA quantitative measure of a specified fairness-related property, often a comparison across groups. Selecting a metric is a normative and contextual choice; satisfying it does not establish fairness in every other sense.[14][15]
FeatureA measured, derived, or encoded input variable supplied to a model. A feature can be numeric, categorical, structured, or represented by multiple coordinates.[3][4]
Feature engineeringSelection, construction, encoding, or transformation of raw observations into model inputs. The transformations must be fit without access to held-out outcomes that would create leakage.[4][9]
Fine-tuningAdditional training of a pretrained model for a new dataset, domain, task, or behavior. Fine-tuning may update all parameters or only a selected subset or added parameters.[3][13]
Foundation modelA model trained on broad data, usually at scale, that can be adapted to many downstream tasks. The category concerns broad upstream training and downstream adaptation, not one architecture or a guarantee of general competence.[13]

G-L

TermDefinition
GeneralizationPerformance on relevant examples not used to fit the model. A generalization claim is bounded by the population, task, time period, and evaluation procedure from which it is estimated.[4]
Generative adversarial networkA generative framework in which a generator and discriminator are trained in opposition: the generator tries to imitate the data distribution while the discriminator tries to distinguish generated from observed samples.[16]
Generative modelA model of a data distribution, joint distribution, or conditional distribution that can support generation or likelihood-related tasks. Some generative models define an explicit density and others generate samples only implicitly.[5]
GeneratorIn a generative adversarial network, the model that transforms noise or another input into candidate samples intended to resemble data from the target distribution.[16]
GradientThe vector of partial derivatives of a scalar quantity with respect to selected variables. In training, gradients describe local sensitivity of an objective to parameter changes.[5]
Gradient boostingA boosting method that adds weak learners in a stagewise fashion to move the ensemble toward lower loss, commonly by fitting directions related to the negative functional gradient.[4]
Gradient descentAn iterative optimization family that changes parameters in the direction opposite the local gradient of an objective. Step size, gradient estimation, curvature, and nonconvexity affect its behavior.[4][5]
HallucinationGenerated content that is nonsensical, unfaithful to provided source content, or inconsistent with relevant facts. Operational definitions differ across generation tasks and must be paired with an evaluation protocol.[3][12][19]
Hidden layerA neural-network layer between the externally supplied input and the designated output. Hidden activations form intermediate representations rather than directly observed target values.[5]
HyperparameterA setting that governs model structure, data processing, or learning and is not fitted as an ordinary model parameter in the same training run. Some hyperparameters are selected through a separate optimization process.[3][4]
Hyperparameter tuningSearch or optimization over hyperparameter choices using training and validation evidence. The untouched test set should not guide this search.[6]
InferenceUse of a fitted model to compute predictions, scores, representations, or generated outputs. In statistics the word can also mean reasoning about populations or latent quantities, so context matters.[1][3]
Intersection over unionThe area or volume of overlap between two regions divided by the area or volume covered by their union. It is commonly used to compare predicted and reference boxes or masks.[3]
K-meansA clustering algorithm that alternates assignment to the nearest centroid with recomputation of centroids to reduce within-cluster squared Euclidean distance. Results can depend on initialization and feature scaling.[4]
LabelA stored target value associated with an example, especially in supervised learning. Labels can be noisy, incomplete, delayed, subjective, or produced by another measurement process.[2][3]
Language modelA model that assigns probabilities to linguistic sequences or predicts tokens conditional on context. The unit may be a character, subword, word, byte, or another token defined by the system.[12]
Large language modelA language model with large learned capacity and broad training data relative to a chosen comparison set. There is no universal parameter-count threshold at which a language model becomes large.[12][13]
Learning rateA hyperparameter that scales an optimizer's update or a component of it. Adaptive optimizers may maintain different effective rates across parameters and training steps.[3][5]
Log lossNegative log-likelihood used to score probabilistic predictions. In binary classification it penalizes confident probability assignments sharply when they disagree with the reference label.[7]
Logistic regressionA generalized linear classification model. In the binary case, it represents class log-odds as a linear function of features; multinomial extensions model more than two classes.[3][4]
Long short-term memoryA gated recurrent architecture whose cell state and gates create paths that can preserve or modify information over many sequence steps. It mitigates, but does not eliminate, long-range optimization problems.[5]
LossA numerical penalty assigned to a prediction, example, or collection of examples. The training objective may aggregate the loss and add regularization or other constraints, so loss and objective are not always synonyms.[3][5]

M-R

TermDefinition
Machine learningThe development or use of computational methods that improve task performance or infer patterns from data or experience. The boundary with statistics, optimization, artificial intelligence, and rule-based programming depends on context.[1][3][4]
Markov decision processA mathematical model of sequential decisions with states, actions, transition probabilities, rewards, and usually a discount or horizon, where the modeled state is sufficient for predicting the next-step distribution given an action.[10]
Matrix factorizationApproximation or decomposition of a matrix as a product of lower-dimensional factors. In recommendation, user and item factors can model interaction patterns but do not by themselves solve cold-start or feedback-bias problems.[3]
Mini-batchA subset of training examples used to estimate a gradient or perform one update. Mini-batch training lies between single-example stochastic updates and full-batch updates.[3][5]
ModelA fitted mathematical or computational object that maps inputs, represents a distribution, or supports decisions. The word can refer narrowly to learned parameters or more broadly to their architecture and execution logic.[1][2]
Multiclass classificationClassification in which one example is assigned among more than two classes. It differs from multilabel classification, where multiple labels can be true for the same example.[7]
Multimodal modelA model designed to consume, relate, or produce information in more than one modality, such as text, images, audio, or video. Multimodal does not imply equal capability in every modality.[13]
Natural language processingComputational analysis or generation of human language and related symbolic sequences. It includes tasks involving text, speech transcripts, structure, meaning, dialogue, retrieval, and generation.[12]
Neural networkA parameterized composition of layers or computational units, commonly trained with gradient-based methods. Network structure, activation functions, objective, and data determine what function is learned.[5]
Objective functionThe scalar quantity an optimization procedure seeks to minimize or maximize. It may combine empirical loss, regularization, constraints, rewards, or surrogate terms.[4][5]
OptimizerThe algorithm that turns gradients or other training signals into parameter updates. Its update rule, internal state, and hyperparameters are distinct from the loss being optimized.[5]
OverfittingLearning patterns that produce strong performance on the fitting data but fail to generalize to the intended population. It is diagnosed with appropriate held-out evidence, not training error alone.[4]
ParameterA value learned or estimated during model fitting, such as a weight, bias, split value, or distribution parameter. This contrasts with a hyperparameter set or selected outside the ordinary fit.[3][4]
PerplexityThe exponential of average negative log-likelihood under a specified unit and dataset, widely used for language models. Values are not directly comparable across different tokenizations, corpora, or normalization conventions.[12]
PolicyA reinforcement-learning rule that maps states, observations, or histories to actions or probability distributions over actions.[10]
PoolingAggregation over a local region or collection, such as maximum or average pooling. In convolutional networks it can reduce spatial resolution and create limited invariance.[5]
Positional encodingInformation supplied to a sequence model so it can distinguish positions or relative order. It may be fixed, learned, absolute, relative, or incorporated directly into attention.[11][12]
PrecisionAmong predictions assigned to a specified positive class, the fraction whose reference label is positive. Its value depends on the threshold and class prevalence in the evaluation data.[7]
PredictionA model output intended to estimate an unknown target, future event, class, score, probability, or structured object. Not every output interpreted as a prediction is a calibrated probability.[2][8]
PretrainingAn initial training phase that produces representations or parameters for later adaptation, prompting, or task-specific learning. The pretraining objective need not match the downstream task.[12][13]
PromptInput supplied to condition a generative or instruction-following model, potentially including instructions, examples, context, tool descriptions, or requested output format.[3][12]
Q-learningAn off-policy temporal-difference method that learns action values toward a target using the best estimated next action, without requiring the behavior policy to be the target policy.[10]
Random forestAn ensemble that combines decision trees while randomizing the candidate features considered at splits. Trees are commonly, but not necessarily, trained on bootstrap samples; both mechanisms can reduce correlation among trees.[4]
RecallAmong reference examples in a specified positive class, the fraction predicted positive. Recall is also called sensitivity or true-positive rate in common binary-classification settings.[7]
Recommender systemA system that selects or ranks items for users or contexts using interaction, content, or other signals.[3]
Rectified linear unitAn activation that returns zero for a negative input and the input itself for a positive input. Its simple derivative supports optimization, though units can become inactive on consistently negative inputs.[5]
Recurrent neural networkA neural network that reuses parameters across sequence steps and updates a hidden representation from prior state and current input. Gated variants modify this recurrence to support longer dependencies.[5]
RegularizationAny training strategy intended to improve generalization by shaping the fitted solution, such as penalties, constraints, augmentation, noise, early stopping, or architectural choices. It is broader than adding a penalty term.[5]
Reinforcement learningLearning how to act through interaction so as to maximize expected return. The formulation requires choices about observations or states, actions, rewards, dynamics, horizon, and policy evaluation.[10]
RepresentationAn encoding of relevant information used internally or exposed as model output. What a representation preserves depends on the data, objective, architecture, and analysis method.[5][13]
ReturnThe accumulated future reward from a time step under a specified horizon and discounting convention. Return, rather than each immediate reward in isolation, is the usual reinforcement-learning objective signal.[10]
RewardThe immediate scalar feedback emitted by a reinforcement-learning environment after a transition or action. A reward defines part of the task but may be an imperfect proxy for the intended outcome.[10]
ROC curveA curve plotting true-positive rate against false-positive rate as a binary decision threshold varies. It summarizes score discrimination across thresholds, not probability calibration.[7][8]

S-Z

TermDefinition
Self-attentionAttention in which queries, keys, and values are derived from positions in the same sequence or representation. Masks can restrict which positions are allowed to interact.[11]
Semi-supervised learningLearning from a combination of labeled and unlabeled examples. Its benefit depends on assumptions connecting the unlabeled-data structure to the prediction task.[3]
Sensitive attributeA characteristic used to define groups for fairness, privacy, or discrimination analysis, such as age or race in some contexts. Which attributes are protected and how they may be used depend on jurisdiction and application.[15]
Sequence modelA model whose inputs, outputs, or internal dependencies are ordered. Recurrent networks, convolutional sequence models, state-space models, and transformers are different sequence-model families.[5][12]
Sequence-to-sequence taskA task mapping an input sequence to an output sequence whose length may differ, such as translation, transcription, or summarization.[12]
SoftmaxA function that turns a vector of finite real-valued scores into positive values summing to one. Treating them as probabilities still depends on the model, objective, and calibration.[5][8]
StateIn a Markov decision process, information sufficient to determine the distribution of the next state and reward given an action. An agent's observation can be an incomplete or noisy view of that state.[10]
Stochastic gradient descentGradient-based optimization using a noisy estimate computed from one example or a mini-batch rather than the complete training set. Usage often includes mini-batch SGD even though the literal cases differ.[4][5]
Supervised learningLearning a mapping or predictive rule from examples paired with target values. Labels may be measured or annotated and are not automatically complete or error-free ground truth.[3][4]
TensorA multidimensional array in common machine-learning software usage. Its rank is the number of dimensions and its shape records the size along each dimension.[3]
Test setHeld-out examples reserved for final evaluation after model and hyperparameter choices. Reusing test results to guide development turns the set into another validation source.[6][9]
TokenA unit emitted by a tokenizer and consumed or predicted by a language model. It may represent a word, word piece, character, byte, punctuation mark, or another learned unit rather than the smallest linguistic element.[12]
TokenizationConversion of text or another input into a sequence of tokens under a defined vocabulary and algorithm. Tokenization choices affect sequence length, model inputs, and evaluation quantities such as perplexity.[12]
TrainingThe process of fitting model parameters or behavior from data, feedback, or interaction according to an objective and optimization procedure.[1][3]
Training setThe examples used to fit model parameters. Transformations learned from data, including scaling and feature selection, should be fit using the training portion rather than held-out data.[6][9]
Transfer learningReuse of parameters, representations, or knowledge learned in one setting to improve learning or performance in another. Transfer can help, fail, or harm when source and target differ.[3][13]
TransformerA sequence architecture centered on attention, position information, feed-forward transformations, residual connections, and normalization. The original encoder-decoder design removed recurrence and convolution, while later transformer variants modify its components.[11]
UnderfittingFailure to capture enough task-relevant structure, producing inadequate performance even on data representative of the fitting objective. It can result from limited model capacity, features, optimization, or training.[4]
Unsupervised learningLearning structure or representations from inputs without task labels of the supervised kind. Clustering, density estimation, dimensionality reduction, and some representation-learning methods fall under this broad heading.[3][4]
Validation setHeld-out data used during development for choices such as hyperparameters, stopping, thresholds, or model selection. Because those choices adapt to it, final performance should be estimated on separate test data.[6]
Vanishing gradientA training difficulty in which derivatives shrink through many composed operations, leaving early parameters with little learning signal. Gating, residual paths, normalization, and activation choices can change the problem.[5]
Variational autoencoderA latent-variable generative model trained with variational inference by optimizing a lower bound that balances reconstruction or likelihood fit against a divergence involving the approximate latent posterior.[17]
WeightA learned coefficient that controls the contribution of an input or intermediate activation. Neural-network weights are parameters, but not every parameter is necessarily called a weight.[3][5]
Word embeddingA vector representation associated with a word or word type. Context-independent word embeddings assign one stored vector per vocabulary item, while contextual models produce representations that vary with surrounding text.[12]
Zero-shot learningPerforming a task or recognizing a class without labeled training examples specific to that task or class, typically by transferring semantic descriptions, instructions, or broadly learned representations. Exact usage varies by subfield.[3][13]

Reading and maintaining the glossary

A short definition should be treated as an entry point, not as a substitute for task documentation. Before comparing metrics, identify the dataset, split, population, target, averaging rule, threshold, and uncertainty. Before comparing language models, also identify tokenization, prompt, decoding settings, tools, and evaluation protocol. Before interpreting a fairness result, state the protected groups, reference outcome, decision context, and criterion selected.[6][7][8][12][14][15]

Terminology changes when methods cross disciplines. The safest interpretation is the narrowest one supported by the surrounding paper, standard, or implementation. If an article uses a word differently, that local definition controls its argument. This page should therefore be updated when a definition becomes misleading or a durable term becomes common, but it should not become a changelog for frameworks or a leaderboard for current systems.

References

  1. ^International Organization for Standardization and International Electrotechnical Commission, "ISO/IEC 22989:2022 Information technology - Artificial intelligence - Artificial intelligence concepts and terminology," 2022. iso.org/...74296
  2. ^National Institute of Standards and Technology, "The Language of Trustworthy AI: An In-Depth Glossary of Terms," beta glossary, accessed 28 July 2026. airc.nist.gov/glossary
  3. ^Google for Developers, "Machine Learning Glossary," accessed 28 July 2026. developers.google.com/...glossary
  4. ^Gareth James, Daniela Witten, Trevor Hastie, and Robert Tibshirani, "An Introduction to Statistical Learning," second R edition, 2021; and Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani, and Jonathan Taylor, Python edition, 2023, official book site. statlearning.com
  5. ^Ian Goodfellow, Yoshua Bengio, and Aaron Courville, "Deep Learning," MIT Press, 2016, official book site. deeplearningbook.org
  6. ^scikit-learn, "Cross-validation: evaluating estimator performance," version 1.9.0 documentation, accessed 28 July 2026. scikit-learn.org/...cross_validation
  7. ^scikit-learn, "Metrics and scoring: quantifying the quality of predictions," version 1.9.0 documentation, accessed 28 July 2026. scikit-learn.org/...model_evaluation
  8. ^scikit-learn, "Probability calibration," version 1.9.0 documentation, accessed 28 July 2026. scikit-learn.org/...calibration
  9. ^scikit-learn, "Common pitfalls and recommended practices," version 1.9.0 documentation, accessed 28 July 2026. scikit-learn.org/...common_pitfalls
  10. ^Richard S. Sutton and Andrew G. Barto, "Reinforcement Learning: An Introduction," second edition, MIT Press, 2018. mitpress.mit.edu/...reinforcement-learning
  11. ^Ashish Vaswani et al., "Attention Is All You Need," 2017. arxiv.org/...1706.03762
  12. ^Daniel Jurafsky and James H. Martin, "Speech and Language Processing," third edition draft, online manuscript released 6 January 2026. web.stanford.edu/...slp3
  13. ^Rishi Bommasani et al., "On the Opportunities and Risks of Foundation Models," 2021. arxiv.org/...2108.07258
  14. ^Moritz Hardt, Eric Price, and Nati Srebro, "Equality of Opportunity in Supervised Learning," Advances in Neural Information Processing Systems 29, 2016. proceedings.neurips.cc/...7384ba499518b38-Abstract
  15. ^National Institute of Standards and Technology, "Towards a Standard for Identifying and Managing Bias in Artificial Intelligence," NIST Special Publication 1270, March 2022. doi.org/...NIST.SP.1270
  16. ^Ian Goodfellow et al., "Generative Adversarial Nets," Advances in Neural Information Processing Systems 27, 2014. proceedings.neurips.cc/...9a61f95710dbe25-Abstract
  17. ^Diederik P. Kingma and Max Welling, "Auto-Encoding Variational Bayes," 2013. arxiv.org/...1312.6114
  18. ^Jonathan Ho, Ajay Jain, and Pieter Abbeel, "Denoising Diffusion Probabilistic Models," Advances in Neural Information Processing Systems 33, 2020. proceedings.neurips.cc/...67f1ab10179ca4b-Abstract
  19. ^Ziwei Ji et al., "Survey of Hallucination in Natural Language Generation," ACM Computing Surveys 55(12), article 248, 2023. doi.org/...3571730

Improve this article

Add missing citations, update stale details, or suggest a clearer explanation. Every suggestion is reviewed for sourcing before it goes live.

7 revisions · v8 · 5,692 words · full history

Fact-checks are independent of edits: a reviewer re-verifies the article against its sources and stamps the date. How we verify

Research and drafting on this wiki are AI-assisted, under named human editorial standards. How AI is used here

Reviewer note: Independently verified against 19 primary, peer-reviewed, official, and author-maintained sources covering terminology scope, statistical learning, deep learning, evaluation, calibration, leakage, reinforcement learning, transformers, language processing, foundation models, fairness, bias, generative models, and hallucination; all 139 definitions, 203 citation calls, bibliographic metadata, source boundaries, and current documentation checked through 2026-07-28.

Cite this page: AI Wiki. "Machine learning terms." aiwiki.ai, updated 28 Jul 2026, fact-checked 28 Jul 2026. CC BY 4.0. https://aiwiki.ai/wiki/machine_learning_terms

Suggest edit