Results for "regression loss"

Automated detection/prevention of disallowed outputs (toxicity, self-harm, illegal instruction, etc.).

Predicting future values from past observations.

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

Persistent directional movement over time.

Systematic error introduced by simplifying assumptions in a learning algorithm.

Expected causal effect of a treatment.

Estimating parameters by maximizing likelihood of observed data.

Low-latency prediction per request.

Running predictions on large datasets periodically.

Mathematical foundation for ML involving vector spaces, matrices, and linear transformations.

Number of linearly independent rows or columns.

Measure of spread around the mean.

Measures joint variability between variables.

Probabilities do not reflect true correctness.

Requirement to provide explanations.

Ability to correctly detect disease.

AI that ranks patients by urgency.

Grouping patients by predicted outcomes.

AI predicting crime patterns (highly controversial).

Models estimating recidivism risk.

Predicting case success probabilities.

Identifying suspicious transactions.

Predicting borrower default risk.

Credit models with interpretable logic.

Fast approximation of costly simulations.

Reusing knowledge from a source task/domain to improve learning on a target task/domain, typically via pretrained models.

Learning where data arrives sequentially and the model updates continuously, often under changing distributions.

Training one model on multiple tasks simultaneously to improve generalization through shared structure.

Methods that learn training procedures or initializations so models can adapt quickly to new tasks with little data.

Techniques that discourage overly complex solutions to improve generalization (reduce overfitting).