supervised learning

(redirected from Empirical risk minimization)
Also found in: Acronyms.

supervised learning

A machine learning training method that trains a neural network by feeding it predefined sets of inputs and outputs. Supervised learning causes the network to learn by example. The network is fed pre-labeled input-output pairs so that it adjusts itself to recognize which input patterns produce which outputs.

Contrast with "unsupervised learning," whereby there are no input-output labels. The network differentiates the unknown input as a series of patterns. See machine learning and deep learning.
Copyright © 1981-2019 by The Computer Language Company Inc. All Rights reserved. THIS DEFINITION IS FOR PERSONAL USE ONLY. All other reproduction is strictly prohibited without permission from the publisher.
Full browser ?