Stability (learning theory)

id: stability-learning-theory-223-2127007
title: Stability (learning theory)
text: Stability, also known as algorithmic stability, is a notion in computational learning theory of how a machine learning algorithm output is changed with small perturbations to its inputs. A stable learning algorithm is one for which the prediction does not change much when the training data is modified slightly. For instance, consider a machine learning algorithm that is being trained to recognize handwritten letters of the alphabet, using 1000 examples of handwritten letters and their labels as
brand slug: wiki
category slug: encyclopedia
description: Change in a machine learning algorithm's accuracy when the training data is modified
original url: https://en.wikipedia.org/wiki/Stability_(learning_theory)
date created: 2011-11-27T19:46:20Z
date modified: 2024-09-14T08:57:57Z
main entity: {"identifier":"Q7595718","url":"https://www.wikidata.org/entity/Q7595718"}
image:
fields total: 13
integrity: 15

Related Entries

Explore Next Part