Interpretable Embeddings From Molecular Simulations Using Gaussian Mixture Variational Autoencoders

1 code implementation • 22 Dec 2019 • Yasemin Bozkurt Varolgunes, Tristan Bereau, Joseph F. Rudzinski

While variational autoencoders ensure continuity of the embedding by assuming a unimodal Gaussian prior, this is at odds with the multi-basin free-energy landscapes that typically arise from the identification of meaningful collective variables.

Clustering Dimensionality Reduction +1