Results for "samples"
Batch Size
Intermediate
Number of samples per gradient update; impacts compute efficiency, generalization, and stability.
Active Learning
Intermediate
Selecting the most informative samples to label (e.g., uncertainty sampling) to reduce labeling cost.
Curriculum Learning
Intermediate
Ordering training samples from easier to harder to improve convergence or generalization.
Top-k
Intermediate
Samples from the k highest-probability tokens to limit unlikely outputs.
Top-p
Intermediate
Samples from the smallest set of tokens whose probabilities sum to p, adapting set size by context.
PAC Learning
Intermediate
A model is PAC-learnable if it can, with high probability, learn an approximately correct hypothesis from finite samples.
Generative Model
Advanced
Models that learn to generate samples resembling training data.