Geometric Methods in Deep Learning

Ünal, İ̇nan; Yıldırım, Özal

doi:10.1109/asyu.2018.8554021

Search citation statements

Order By: Relevance

Paper Sections

Select...

Introduction1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2021

Publication Types

Select...

Other1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, geometric and topological methods have important roles in learning neural networks, pattern recognition and signal processing [2], [24]. The main idea in these areas is to consider a flat or curved network parameter space endowed with a suitable geometric structure in the network learning algorithm.…”

Section: Introductionmentioning

confidence: 99%

Homology of contact CR-submanifolds

Şahin¹,

Şahin²

2021

Preprint

View full text Add to dashboard Cite

In this paper, homology of a contact CR-submanifold of a real hypersurface, which has naturally almost contact metric structure induced from the complex Euclidean space C m , is examined. More precisely, nonexistence of stable integral currents on a compact contact CR-submanifold of real hypersurface of canonical complex space form C m is investigated and vanishing theorems concerning the homology groups are obtained.

show abstract

Section: Introductionmentioning

confidence: 99%