Results for "input variable"

Variable enabling causal inference despite confounding.

Reduction in uncertainty achieved by observing a variable; used in decision trees and active learning.

A hidden variable influences both cause and effect, biasing naive estimates of causal impact.

Quantifies shared information between random variables.

Variable whose values depend on chance.

Describes likelihoods of random variable outcomes.

Average value under a distribution.

Differences between training and deployed patient populations.

Measures how much information an observable random variable carries about unknown parameters.

Graphical model expressing factorization of a probability distribution.

Formal model linking causal mechanisms and variables.

Models effects of interventions (do(X=x)).

A parameterized mapping from inputs to outputs; includes architecture + learned parameters.

Chooses which experts process each token.

The relationship between inputs and outputs changes over time, requiring monitoring and model updates.

Assigning a role or identity to the model.

Optimizes future actions using a model of dynamics.

Designing input features to expose useful structure (e.g., ratios, lags, aggregations), often crucial outside deep learning.

A single attention mechanism within multi-head attention.

A measure of randomness or uncertainty in a probability distribution.

Measures how one probability distribution diverges from another.

Exact likelihood generative models using invertible transforms.

When information from evaluation data improperly influences training, inflating reported performance.

Directed acyclic graph encoding causal relationships.

What would have happened under different conditions.

Expected causal effect of a treatment.

Measure of spread around the mean.

Measures joint variability between variables.

Sample mean converges to expected value.

Approximating expectations via random sampling.