HIGHLIGHTS
- who: Aniss Aiman Medbouhi and colleagues from the Division of Robotics Perception and Learning, Department of Intelligent Systems, School of Electrical Engineering have published the research: InvMap and Witness Simplicial Variational Auto-Encoders, in the Journal: (JOURNAL)
- what: The authors propose two different approaches with the aim to preserve the topological structure between the input space and the latent representation of a VAE. The authors propose the VAE as an extension of the auto-encoder to the setup using a complex for computing the regularization and the authors motivate this method theoretically using tools from . . .
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.