Beyond Euclid: an illustrated guide to modern machine learning with geometric, topological, and algebraic structures

Kaydedildi:
Detaylı Bibliyografya
Yayımlandı:Machine Learning : Science and Technology vol. 6, no. 3 (Sep 2025), p. 031002
Yazar: Papillon, Mathilde
Diğer Yazarlar: Sanborn, Sophia, Mathe, Johan, Cornelis, Louisa, Bertics, Abby, Domas Buracas, Lillemark, Hansen J, Shewmake, Christian, Dinc, Fatih, Pennec, Xavier, Miolane, Nina
Baskı/Yayın Bilgisi:
IOP Publishing
Konular:
Online Erişim:Citation/Abstract
Full Text - PDF
Etiketler: Etiketle
Etiket eklenmemiş, İlk siz ekleyin!

MARC

LEADER 00000nab a2200000uu 4500
001 3235721227
003 UK-CbPIL
022 |a 2632-2153 
024 7 |a 10.1088/2632-2153/adf375  |2 doi 
035 |a 3235721227 
045 2 |b d20250901  |b d20250930 
100 1 |a Papillon, Mathilde  |u UC Santa Barbara , Santa Barbara, United States of America; Equal contribution 
245 1 |a Beyond Euclid: an illustrated guide to modern machine learning with geometric, topological, and algebraic structures 
260 |b IOP Publishing  |c Sep 2025 
513 |a Journal Article 
520 3 |a The enduring legacy of Euclidean geometry underpins classical machine learning, which, for decades, has been primarily developed for data lying in Euclidean space. Yet, modern machine learning increasingly encounters richly structured data that is inherently non-Euclidean. This data can exhibit intricate geometric, topological and algebraic structure: from the geometry of the curvature of space-time, to topologically complex interactions between neurons in the brain, to the algebraic transformations describing symmetries of physical systems. Extracting knowledge from such non-Euclidean data necessitates a broader mathematical perspective. Echoing the 19th-century revolutions that gave rise to non-Euclidean geometry, an emerging line of research is redefining modern machine learning with non-Euclidean structures. Its goal: generalizing classical methods to unconventional data types with geometry, topology, and algebra. In this review, we provide an accessible gateway to this fast-growing field and propose a graphical taxonomy that integrates recent advances into an intuitive unified framework. We subsequently extract insights into current challenges and highlight exciting opportunities for future development in this field. 
653 |a Structured data 
653 |a Taxonomy 
653 |a Machine learning 
653 |a Algebra 
653 |a Euclidean space 
653 |a Geometry 
653 |a Euclidean geometry 
653 |a Topology 
700 1 |a Sanborn, Sophia  |u Stanford University , Palo Alto, United States of America; Equal contribution 
700 1 |a Mathe, Johan  |u Atmo, Inc., San Francisco , United States of America; Equal contribution 
700 1 |a Cornelis, Louisa  |u UC Santa Barbara , Santa Barbara, United States of America; Equal contribution 
700 1 |a Bertics, Abby  |u UC Santa Barbara , Santa Barbara, United States of America 
700 1 |a Domas Buracas  |u New Theory AI , San Francisco, United States of America 
700 1 |a Lillemark, Hansen J  |u New Theory AI , San Francisco, United States of America; UC Berkeley , Berkeley, United States of America 
700 1 |a Shewmake, Christian  |u New Theory AI , San Francisco, United States of America 
700 1 |a Dinc, Fatih  |u UC Santa Barbara , Santa Barbara, United States of America 
700 1 |a Pennec, Xavier  |u Université Côte d’Azur & Inria , Nice, France 
700 1 |a Miolane, Nina  |u UC Santa Barbara , Santa Barbara, United States of America; Stanford University , Palo Alto, United States of America; Atmo, Inc., San Francisco , United States of America; New Theory AI , San Francisco, United States of America 
773 0 |t Machine Learning : Science and Technology  |g vol. 6, no. 3 (Sep 2025), p. 031002 
786 0 |d ProQuest  |t Science Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3235721227/abstract/embedded/J7RWLIQ9I3C9JK51?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3235721227/fulltextPDF/embedded/J7RWLIQ9I3C9JK51?source=fedsrch