Hybrid autoencoder with orthogonal latent space for robust population structure inference

HIGHLIGHTS

• who: Meng Yuan from the DepartmentUniversity Hospitals have published the Article: Hybrid autoencoder with orthogonal latent space for robust population structure inference, in the Journal: Scientific Reports Scientific Reports
• what: The authors proposed a hybrid method for population structure inference, SAE-IBS, which yields an orthogonal latent space, like matrix decomposition-based methods, and can extract more comprehensive latent features by exploiting the non-linear nature of neural_network-based methods. Motivation, the authors propose to include an extra robust projection loss (mathematical details in additional file 1) in the original objective function, yielding a denoising . . .
  

   

  

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

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

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