Show simple item record

dc.contributor.advisorLin, Kevin
dc.contributor.authorGordon, Andrew
dc.creatorGordon, Andrew
dc.date.accessioned2020-02-13T03:02:01Z
dc.date.available2020-02-13T03:02:01Z
dc.date.issued2019-12
dc.identifier.urihttp://hdl.handle.net/10150/637027
dc.description.abstractMost of statistical machine learning relies on deep neural nets, whose underlying theory and mathematical properties are currently not well explored. This thesis focuses on the theory of Perceptrons, a form of shallow neural network mostly explored in Minsky & Papert’s book “Perceptrons: an Introduction to Computational Geometry”. Their analysis relied on the use of groups that describe the global symmetries of what is to be computed. However, all real images have an input space with finite length and height, and it is often the case that machine learning systems have disconnected input spaces. This means that real-world systems must actually rely on a concept of local symmetry, if any at all. This paper explores the implications of having a bounded and possibly disconnected input space, and generalizes the Minsky & Papert result, proving that the implications of the group invariance theorem can be retained by using groupoids instead.en_US
dc.language.isoenen_US
dc.publisherThe University of Arizona.en_US
dc.rightsCopyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.en_US
dc.titleExtension of the Group Invariance Theorem for Perceptronsen_US
dc.typetexten_US
dc.typeElectronic Thesisen_US
thesis.degree.grantorUniversity of Arizonaen_US
thesis.degree.levelbachelorsen_US
thesis.degree.disciplineHonors Collegeen_US
thesis.degree.disciplineMathematics
thesis.degree.nameB.A.en_US
refterms.dateFOA2020-02-13T03:02:01Z


Files in this item

Thumbnail
Name:
azu_etd_hr_2019_0256_sip1_m.pdf
Size:
2.293Mb
Format:
PDF
Description:
Honors Thesis

This item appears in the following Collection(s)

Show simple item record