Alert button
Picture for Daniel G. Edelberg

Daniel G. Edelberg

Alert button

Using VAEs to Learn Latent Variables: Observations on Applications in cryo-EM

Add code
Bookmark button
Alert button
Mar 13, 2023
Daniel G. Edelberg, Roy R. Lederman

Figure 1 for Using VAEs to Learn Latent Variables: Observations on Applications in cryo-EM
Figure 2 for Using VAEs to Learn Latent Variables: Observations on Applications in cryo-EM
Figure 3 for Using VAEs to Learn Latent Variables: Observations on Applications in cryo-EM
Figure 4 for Using VAEs to Learn Latent Variables: Observations on Applications in cryo-EM

Variational autoencoders (VAEs) are a popular generative model used to approximate distributions. The encoder part of the VAE is used in amortized learning of latent variables, producing a latent representation for data samples. Recently, VAEs have been used to characterize physical and biological systems. In this case study, we qualitatively examine the amortization properties of a VAE used in biological applications. We find that in this application the encoder bears a qualitative resemblance to more traditional explicit representation of latent variables.

Viaarxiv icon
Github IconAccess Paper or Ask Questions
Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon