Results for "performance"

System for running consistent evaluations across tasks, versions, prompts, and model settings.

Maliciously inserting or altering training data to implant backdoors or degrade performance.

Capabilities that appear only beyond certain model sizes.

Assigning category labels to images.

End-to-end process for model training.

Running new model alongside production without user impact.

Incrementally deploying new models to reduce risk.

Increasing model capacity via compute.

Scaling law optimizing compute vs data.

Cost of model training.

Declining differentiation among models.

Required descriptions of model behavior and limits.

Maximum system processing rate.

Dynamic resource allocation.

Storing results to reduce compute.

The physical system being controlled.

Performance drop when moving from simulation to reality.

Ability to correctly detect disease.

Unequal performance across demographic groups.

Training a smaller “student” model to mimic a larger “teacher,” often improving efficiency while retaining performance.

A subfield of AI where models learn patterns from data to make predictions or decisions, improving with experience rather than explicit rule-coding.

Learning a function from input-output pairs (labeled data), optimizing performance on predicting outputs for unseen inputs.

Training with a small labeled dataset plus a larger unlabeled dataset, leveraging assumptions like smoothness/cluster structure.

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

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

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

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.

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

Configuration choices not learned directly (or not typically learned) that govern training or architecture.