About: Stability (learning theory)

Facets (new session)
Description
Metadata
Settings
- Rule:
- Inverse Functional Properties:
- "Same As":

About: Stability (learning theory) Goto Sponge NotDistinct Permalink

An Entity of Type : dbo:Country, within Data Space : dbpedia.demo.openlinksw.com associated with source document(s)
QRcode icon

http://dbpedia.demo.openlinksw.com/describe/?url=http%3A%2F%2Fdbpedia.org%2Fresource%2FStability_%28learning_theory%29

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.

Attributes	Values
rdf:type	country
rdfs:label	Stability (learning theory) (en)
rdfs:comment	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. (en)
dcterms:subject	Machine learning Learning
Wikipage page ID	33886025 (xsd:integer)
Wikipage revision ID	1119197371 (xsd:integer)
Link from a Wikipage to another Wikipage	Natural language processing Vladimir Vapnik Inverse problem Consistent estimator Regularization (machine learning) Andrey Nikolayevich Tikhonov Machine learning Computational learning theory Empirical risk minimization Machine learning Linear regression Learning Handwriting recognition Uniform convergence Support Vector Machine Bootstrap aggregating Sensitivity analysis VC dimension Statistical classification Supervised learning Leave one out error VC theory
sameAs	Stability (learning theory) Stability (learning theory) Stability (learning theory)
dbp:wikiPageUsesTemplate	dbt:Citation_needed dbt:Refbegin dbt:Refend dbt:Reflist dbt:Short_description
has abstract	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. Stability can be studied for many types of learning problems, from language learning to inverse problems in physics and engineering, as it is a property of the learning process rather than the type of information being learned. The study of stability gained importance in computational learning theory in the 2000s when it was shown to have a connection with generalization. It was shown that for large classes of learning algorithms, notably empirical risk minimization algorithms, certain types of stability ensure good generalization. (en)
gold:hypernym	Notion
prov:wasDerivedFrom	wikipedia-en:Stability_(learning_theory)?oldid=1119197371&ns=0
page length (characters) of wiki page	16248 (xsd:nonNegativeInteger)
foaf:isPrimaryTopicOf	wikipedia-en:Stability_(learning_theory)
is Link from a Wikipage to another Wikipage of	Vapnik–Chervonenkis theory Generalization error Cross-validation (statistics) Computational learning theory Stability Activation function Bootstrap aggregating Outline of machine learning Algorithmic stability Stability in learning
is Wikipage redirect of	Algorithmic stability Stability in learning
is Wikipage disambiguates of	Stability
is foaf:primaryTopic of	wikipedia-en:Stability_(learning_theory)

Faceted Search & Find service v1.17_git139 as of Feb 29 2024

Alternative Linked Data Documents: ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 08.03.3330 as of Mar 19 2024, on Linux (x86_64-generic-linux-glibc212), Single-Server Edition (378 GB total memory, 59 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software