About: Sample complexity

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

About: Sample complexity Goto Sponge NotDistinct Permalink

An Entity of Type : owl:Thing, 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%2FSample_complexity&invfp=IFP_OFF&sas=SAME_AS_OFF

The sample complexity of a machine learning algorithm represents the number of training-samples that it needs in order to successfully learn a target function. More precisely, the sample complexity is the number of training-samples that we need to supply to the algorithm, so that the function returned by the algorithm is within an arbitrarily small error of the best possible function, with probability arbitrarily close to 1. There are two variants of sample complexity:

Attributes	Values
rdfs:label	Sample complexity (en)
rdfs:comment	The sample complexity of a machine learning algorithm represents the number of training-samples that it needs in order to successfully learn a target function. More precisely, the sample complexity is the number of training-samples that we need to supply to the algorithm, so that the function returned by the algorithm is within an arbitrarily small error of the best possible function, with probability arbitrarily close to 1. There are two variants of sample complexity: (en)
dcterms:subject	Machine learning
Wikipage page ID	43269516 (xsd:integer)
Wikipage revision ID	1068917677 (xsd:integer)
Link from a Wikipage to another Wikipage	No free lunch in search and optimization Vapnik–Chervonenkis theory Probably approximately correct learning Online machine learning Monte Carlo tree search Machine learning Empirical risk minimization Machine learning Active learning (machine learning) No free lunch theorem Rademacher complexity Random variable Regularization (mathematics) Reinforcement learning Tikhonov regularization Model-free (reinforcement learning) Metric learning Semi-supervised learning VC dimension Glivenko-Cantelli class Dictionary learning
sameAs	Sample complexity Sample complexity Sample complexity Sample complexity
dbp:wikiPageUsesTemplate	dbt:Reflist dbt:Machine_learning_bar
has abstract	The sample complexity of a machine learning algorithm represents the number of training-samples that it needs in order to successfully learn a target function. More precisely, the sample complexity is the number of training-samples that we need to supply to the algorithm, so that the function returned by the algorithm is within an arbitrarily small error of the best possible function, with probability arbitrarily close to 1. There are two variants of sample complexity: * The weak variant fixes a particular input-output distribution; * The strong variant takes the worst-case sample complexity over all input-output distributions. The No free lunch theorem, discussed below, proves that, in general, the strong sample complexity is infinite, i.e. that there is no algorithm that can learn the globally-optimal target function using a finite number of training samples. However, if we are only interested in a particular class of target functions (e.g, only linear functions) then the sample complexity is finite, and it depends linearly on the VC dimension on the class of target functions. (en)
prov:wasDerivedFrom	wikipedia-en:Sample_complexity?oldid=1068917677&ns=0
page length (characters) of wiki page	14205 (xsd:nonNegativeInteger)
foaf:isPrimaryTopicOf	wikipedia-en:Sample_complexity
is Link from a Wikipage to another Wikipage of	M-theory (learning framework) Prior-independent mechanism Probably approximately correct learning Artificial intelligence Outline of machine learning Random-sampling mechanism Sample-complexity bounds
is Wikipage redirect of	Sample-complexity bounds
is foaf:primaryTopic of	wikipedia-en:Sample_complexity

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, 56 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software