Training Corpus
A training corpus is the collection of text, images, audio, or other examples used to train a model.
Category
Training Pipelines
These words describe training data, optimization steps, and saved model states.
How to recognize this theme
Terms used while an AI model learns from data.
In a daily board, this category groups terms by their shared role. Look for four cards that describe the same mechanism, risk area, or workflow rather than four words that merely sound similar.
Educational context
These entries are vocabulary notes for learning. They are not project endorsements, token recommendations, exchange rankings, or trading signals.
Mini-Batch
A mini-batch is a subset of training examples processed together during one optimization step.
Gradient Descent
Gradient descent updates model parameters in a direction intended to reduce the training loss.
Checkpoint
A checkpoint stores model parameters and related training state so work can be resumed or evaluated later.