Results for "sensitivity to data"

Probability of data given parameters.

Updated belief after observing data.

Enables external computation or lookup.

Running models locally.

Requirement to preserve relevant data.

Trend reversal when data is aggregated improperly.

A structured collection of examples used to train/evaluate models; quality, bias, and coverage often dominate outcomes.

A measurable property or attribute used as model input (raw or engineered), such as age, pixel intensity, or token ID.

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

The learned numeric values of a model adjusted during training to minimize a loss function.

When a model cannot capture underlying structure, performing poorly on both training and test data.

How well a model performs on new data drawn from the same (or similar) distribution as training.

Systematic differences in model outcomes across groups; arises from data, labels, and deployment context.

Measure of consistency across labelers; low agreement indicates ambiguous tasks or poor guidelines.

Selecting the most informative samples to label (e.g., uncertainty sampling) to reduce labeling cost.

Structured dataset documentation covering collection, composition, recommended uses, biases, and maintenance.

Logging hyperparameters, code versions, data snapshots, and results to reproduce and compare experiments.

Systematic review of model/data processes to ensure performance, fairness, security, and policy compliance.

Attacks that infer whether specific records were in training data, or reconstruct sensitive training examples.

Methods to protect model/data during inference (e.g., trusted execution environments) from operators/attackers.

Built-in assumptions guiding learning efficiency and generalization.

Systematic error introduced by simplifying assumptions in a learning algorithm.

Detecting unauthorized model outputs or data leaks.

Estimating parameters by maximizing likelihood of observed data.

Neural networks that operate on graph-structured data by propagating information along edges.

Models that define an energy landscape rather than explicit probabilities.

Learns the score (∇ log p(x)) for generative sampling.

Two-network setup where generator fools a discriminator.

Exact likelihood generative models using invertible transforms.

Attention between different modalities.