Stability (learning theory)
Stability, also known as algorithmic stability, is a notion in computational learning theory of how a machine learning algorithm is perturbed by small changes 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 ("A" to "Z") 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.
Wikipage disambiguates
Wikipage redirect
primaryTopic
Stability (learning theory)
Stability, also known as algorithmic stability, is a notion in computational learning theory of how a machine learning algorithm is perturbed by small changes 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 ("A" to "Z") 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.
has abstract
Stability, also known as algor ...... ty ensure good generalization.
@en
Wikipage page ID
33,886,025
page length (characters) of wiki page
Wikipage revision ID
1,026,004,693
Link from a Wikipage to another Wikipage
wikiPageUsesTemplate
subject
hypernym
type
comment
Stability, also known as algor ...... and 999-element training sets.
@en
label
Stability (learning theory)
@en