Wordt geladen...

A Kernel Theory of Modern Data Augmentation

Data augmentation, a technique in which a training set is expanded with class-preserving transformations, is ubiquitous in modern machine learning pipelines. In this paper, we seek to establish a theoretical framework for understanding data augmentation. We approach this from two directions: First,...

Volledige beschrijving

Bewaard in:
Bibliografische gegevens
Gepubliceerd in:Proc Mach Learn Res
Hoofdauteurs: Dao, Tri, Gu, Albert, Ratner, Alexander J., Smith, Virginia, De Sa, Christopher, Ré, Christopher
Formaat: Artigo
Taal:Inglês
Gepubliceerd in: 2019
Onderwerpen:
Online toegang:https://ncbi.nlm.nih.gov/pmc/articles/PMC6879382/
https://ncbi.nlm.nih.gov/pubmed/31777848
Tags: Voeg label toe
Geen labels, Wees de eerste die dit record labelt!