Golden
Archetypal analysis

Archetypal analysis

Methodology in statistics and unsupervised learning that represents each "individual" in a data set as a mixture of "individuals of pure type", or "archetypes."

All edits

Edits on 12 Mar 2019
Daniel Frumkin
Daniel Frumkin approved a suggestion from Golden's AI on 12 Mar 2019 1:02 pm
Edits made to:
Article (+8/-8 characters)

Article

Archetypal analysis (AA) is a methodology in statistics and unsupervised learning that represents each "individual" in a data setdata set as a mixture of "individuals of pure type", or "archetypes." Computing the archetypes is a nonlinear least squares problem which is solved using an alternative minimizing algorithm. 

Daniel Frumkin
Daniel Frumkin approved a suggestion from Golden's AI on 12 Mar 2019 1:02 pm
Edits made to:
Article (+11/-11 characters)

Article

Archetypal analysis was originally proposed by Adele Cutler and Leo BreimanLeo Breiman as an alternative to principal component analysis (PCA) for discovering latent factors for high-dimensional data. AA estimates the principal convex hull of a data set, and each "archetype" (i.e. factor) is forced to be a convex combination of extremal points of the data. The associations between archetypes and data points contributes to AA's results being easily interpretable.

Edits on 10 Mar 2019
Daniel Frumkin"Added image, description, article, categories, related topics, resources"
Daniel Frumkin edited on 10 Mar 2019 12:57 pm
Edits made to:
Description (+160 characters)
Article (+1243 characters)
People (+2 rows) (+4 cells) (+37 characters)
Further reading (+3 rows) (+12 cells) (+437 characters)
Categories (+2 topics)
Related Topics (+5 topics)
Topic thumbnail

Archetypal analysis

Methodology in statistics and unsupervised learning that represents each "individual" in a data set as a mixture of "individuals of pure type", or "archetypes."

Article

Archetypal analysis (AA) is a methodology in statistics and unsupervised learning that represents each "individual" in a data set as a mixture of "individuals of pure type", or "archetypes." Computing the archetypes is a nonlinear least squares problem which is solved using an alternative minimizing algorithm. 



Archetypal analysis was originally proposed by Adele Cutler and Leo Breiman as an alternative to principal component analysis (PCA) for discovering latent factors for high-dimensional data. AA estimates the principal convex hull of a data set, and each "archetype" (i.e. factor) is forced to be a convex combination of extremal points of the data. The associations between archetypes and data points contributes to AA's results being easily interpretable.



The archetypal analysis methodology allows for dimensionality reduction and clustering. The disadvantage of AA is that its computation costs increase quadratically with the number of data points in a set, making it impractical for most problems. However, robust and efficient algorithms have been developed with practical applications in physics, genetics and phytomedicine, market research and marketing, performance evaluation, behavior analysis, as well as computer vision.









People

Name
Role
Related Golden topics

Adele Cutler

Creator



Leo Breiman

Creator



Further reading

Title
Author
Link
Type

ARCHETYPAL ANALYSIS

Adele Cutler, Leo Breiman

Adademic paper

Archetypal analysis for machine learning and data mining

Morten Morup, Lars Kai Hansen

Web

Making Archetypal Analysis Practical

Christian Bauckhage, Christian Thurau

PDF

Categories

Related Topics

Edits on 1 Jan 2017
Golden AI"Initial topic creation"
Golden AI created this topic on 1 Jan 2017 12:00 am
Edits made to:
Article
Topic thumbnail

 Archetypal analysis

Methodology in statistics and unsupervised learning that represents each "individual" in a data set as a mixture of "individuals of pure type", or "archetypes."

No more activity to show.