Training loss - Training loss is the value of the learning objective measured on examples used to fit a model.
Training oracle - A training oracle is a procedure that uses a known reference answer to provide guidance for a model’s training decisions.
Training Pipeline - A Training Pipeline is an organized sequence of steps that turns selected data and a training configuration into a fitted model and evidence about its...
Training-serving skew - Training-serving skew is a difference between how a model behaves or performs in its training and evaluation setting and how the same model behaves or...
Training set - A training set is the collection of examples used to fit a model's learned parameters.
Trajectory - In reinforcement learning, a trajectory is an ordered sequence of interactions between an agent and its environment.
Trajectory optimization - Trajectory optimization chooses a time-varying sequence of states and controls that minimizes a specified cost while satisfying dynamics and other constraints.
Transaction data - Transaction data records business activities or events, such as an order, a booking or a movement of goods.
Transaction logic - Transaction Logic is a formalism for describing and reasoning about state-changing actions within logic programming and databases.
Transcript-based editing - Transcript-based editing is a way to edit recorded speech and its associated media by selecting and arranging words in a time-linked transcript.
Transduction - Transduction is learning or inference directed at a particular supplied collection of cases, rather than producing a general prediction rule for arbitrary...
Transduction grammars - Transduction grammars are formal systems that describe correspondences between structured expressions, commonly between sentences in two languages.
Transfer-based machine translation - Transfer-based machine translation is an approach that analyses text in a source language, maps the resulting representation into a target-language...
Transfer function - A transfer function describes how an input is transformed into an output by a specified linear system, including delayed effects.
Transfer learning - Transfer learning reuses knowledge learned in one task or setting to help solve another.
Transfer model - A transfer model, in traditional machine translation, maps a representation of a source-language expression into a representation suitable for producing the...
Transform coding - Transform coding compresses data by first expressing it in a different mathematical representation, then encoding the resulting coefficients.
Transformer - A Transformer is a neural-network architecture built around attention mechanisms that combine information from different positions in an input.
Transformer Language Model - A Transformer Language Model is a language model that uses Transformer layers to build contextual token representations and make language predictions.
Transformer Network - A Transformer Network is a neural network assembled from Transformer-style components, especially attention and feed-forward layers that build contextual...
Transient failure - A transient failure is a temporary malfunction that disrupts an observation or operation without necessarily leaving the component permanently broken.
Transient failure model - A transient failure model is a probabilistic description that allows a sensor or component to produce an occasional faulty result without assuming that the...
Transition-based - Transition-based describes an approach that constructs an output through a sequence of state-changing actions.
Transition constraint - A transition constraint is a rule that determines whether a change from one state to another is permitted.
Transition kernel - A transition kernel specifies a probability distribution over possible next states for each current state.
Transition model - A transition model describes how a system moves from its current state to a next state, sometimes depending on an action.
Transition probability - A transition probability is the conditional probability that a system moves to a specified state over a specified step or interval, given its starting state...
Transitive Dependency - A transitive dependency is an indirect functional dependency obtained through an intermediate attribute set.
Transitive Rule - The transitive rule is an inference rule for functional dependencies in relational database theory. If X → Y and Y → Z hold, then X → Z also holds.
Translation-invariant prior - A translation-invariant prior, in the location-parameter sense, assigns the same prior measure to equal-width parameter intervals regardless of where they lie.
Translation memory - A translation memory is a database of previously translated text segments paired with their corresponding translations.
Translation unit - A translation unit is a portion of text treated as a meaningful whole when translating.
Translational invariance - Translational invariance is the property that a model's relevant output remains unchanged when its input is shifted in position.
Transparency - Transparency in AI is the availability of meaningful information about a system, its use, and its outputs to the people who need to understand or assess them.
Transpose - The transpose of a matrix is formed by swapping its row and column positions. An entry originally in row i, column j moves to row j, column i.
Transposition table - A transposition table stores information about game positions that a search has already examined, so the information can be reused when a different sequence...
Traveling salesperson problem - The traveling salesperson problem, or TSP, asks for a minimum-cost tour that visits each required location once and returns to the starting location.
Traversed edges per second - Traversed edges per second, or TEPS, is a performance rate used to describe graph-processing work.
Treatment and control groups - Treatment and control groups are comparison groups used to assess an intervention.
Treatment-confounder feedback - Treatment-confounder feedback occurs when earlier treatment changes a later variable that both influences subsequent treatment and predicts the outcome.
Treatment effect - A treatment effect is the causal difference between outcomes under two specified interventions or treatment conditions.
Tree-based feature selection - Tree-based feature selection uses a fitted decision tree or tree ensemble to help choose which input features a model should retain.
Tree contraction - Tree contraction is an algorithmic technique that repeatedly reduces a tree to a smaller structure while preserving information needed to solve a problem.
Tree decomposition - A tree decomposition represents a graph as overlapping groups of vertices, called bags, connected in a tree.
Tree-like search - Tree-like search explores a tree of possible action sequences without maintaining a global record of every state already reached.
Tree-of-thought prompting - Tree-of-thought prompting organizes language-model problem solving as a search over alternative intermediate steps.
Tree selection policy - A tree selection policy is a rule for choosing which branch to follow while traversing a search tree.