Machine learning in spectral domain

Lorenzo Giambagli, Lorenzo Buffoni, Timoteo Carletti, Walter Nocentini and Duccio Fanelli ()
Additional contact information
Lorenzo Giambagli: Università degli Studi di Firenze, Dipartimento di Fisica e Astronomia, CSDC and INFN
Lorenzo Buffoni: Università degli Studi di Firenze, Dipartimento di Fisica e Astronomia, CSDC and INFN
Timoteo Carletti: University of Namur
Walter Nocentini: Università degli Studi di Firenze, Dipartimento di Fisica e Astronomia, CSDC and INFN
Duccio Fanelli: Università degli Studi di Firenze, Dipartimento di Fisica e Astronomia, CSDC and INFN

Nature Communications, 2021, vol. 12, issue 1, 1-9

Abstract: Abstract Deep neural networks are usually trained in the space of the nodes, by adjusting the weights of existing links via suitable optimization protocols. We here propose a radically new approach which anchors the learning process to reciprocal space. Specifically, the training acts on the spectral domain and seeks to modify the eigenvalues and eigenvectors of transfer operators in direct space. The proposed method is ductile and can be tailored to return either linear or non-linear classifiers. Adjusting the eigenvalues, when freezing the eigenvectors entries, yields performances that are superior to those attained with standard methods restricted to operate with an identical number of free parameters. To recover a feed-forward architecture in direct space, we have postulated a nested indentation of the eigenvectors. Different non-orthogonal basis could be employed to export the spectral learning to other frameworks, as e.g. reservoir computing.

Date: 2021
References: Add references at CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.nature.com/articles/s41467-021-21481-0 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:12:y:2021:i:1:d:10.1038_s41467-021-21481-0

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-021-21481-0

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().