A term that is often used in the context of machine learning. An epoch is one complete presentation of the data set to be learned to a learning machine.

Learning machines like feedforward neural nets that use iterative algorithms often need many epochs during their learning phase.

A discriminant classifier is also a learning machine. However, in contrast with neural nets a discriminant classifier only needs one epoch to learn.

Links to this page

© djmw, April 28, 2004