Contrastive learning via local activity

HIGHLIGHTS

  • who: He Zhu and collaborators from the Institute of Automation (CASIA), Beijing, China School of Future Technology, University of Chinese Academy of Sciences (UCAS), Beijing, China have published the research work: Contrastive Learning via Local Activity, in the Journal: Electronics 2023, 12, 147. of /2023/
  • what: To address these issues in this paper the authors propose the local activity contrast (LAC) algorithm which is an unsupervised method based on two forward passes and locally defined loss to learn meaningful representations. The motivation of this work is, therefore, to find a method for unsupervised learning that . . .

     

    Logo ScioWire Beta black

    If you want to have access to all the content you need to log in!

    Thanks :)

    If you don't have an account, you can create one here.

     

Scroll to Top

Add A Knowledge Base Question !

+ = Verify Human or Spambot ?