Using VAEs to Learn Latent Variables: Observations on Applications in cryo-EM
Abstract: 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 a more traditional explicit representation of latent variables.
Submission Length: Regular submission (no more than 12 pages of main content)
Assigned Action Editor: ~Arnaud_Doucet2
Submission Number: 1323
Loading