A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P, if its performance at tasks in T as measured by P, improves with experience E.
Instance
data point.
Training data
Data for machines to perform learning.
Test data
Data unseen during the learning process, used for evaluating the performance of machines.
Labeled data
Data points with labels.
Unlabeled data
Data points without labels.
Supervised learning
machines learn over labeled data.
Unsupervised learning
machines learn over unlabeled data.
Feature vectors
representation of the data points in the form of vectors.