Detecting errors with zero-shot learning

HIGHLIGHTS

  • who: Xiaoyu Wu and Ning Wang from the School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China have published the Article: Detecting Errors with Zero-Shot Learning, in the Journal: Entropy 2022, 24, 936. of /2022/
  • what: The authors propose an AEGAN (Auto-Encoder Generative Adversarial Network)-based deep learning model named SAT-GAN (Self-Attention Generative Adversarial Network) to detect errors in relational datasets. For the lack of negative samples the authors propose to train the model via zero-shot learning. The authors propose a framework that can recognize error data as . . .

     

    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 ?