a
- Instance of
- Subclass of
Overview
All data
8 statements · 13% with external sources · numbers in brackets are citations
On other databases
3 identifiers linking algorithmic stability across the web's reference databases
8 statements · 13% with external sources · numbers in brackets are citations
3 identifiers linking algorithmic stability across the web's reference databases
From Wikipedia, the free encyclopedia · Read full article · Text CC BY-SA 4.0
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 a training set. One way to modify this training set is to leave out an example, so that only 999 examples of handwritten letters and their labels are available. A stable learning algorithm would produce a similar classifier with both the 1000-element and 999-element training sets.