Search Results for author:
Found 6 papers, 2 papers with code
Neural Langevin Dynamics: towards interpretable Neural Stochastic Differential Equations
Neural Stochastic Differential Equations (NSDE) have been trained as both Variational Autoencoders, and as GANs.
Universal Approximation in Dropout Neural Networks
The first theorem applies to dropout networks in the random mode.
A Metric for Linear Symmetry-Based Disentanglement
We propose a metric for the evaluation of the level of LSBD that a data representation achieves.
Quantifying and Learning Linear Symmetry-Based Disentanglement
The definition of Linear Symmetry-Based Disentanglement (LSBD) formalizes the notion of linearly disentangled representations, but there is currently no metric to quantify LSBD.
Quantifying and Learning Disentangled Representations with Limited Supervision
Although several works focus on learning LSBD representations, such methods require supervision on the underlying transformations for the entire dataset, and cannot deal with unlabeled data.
Diffusion Variational Autoencoders
A standard Variational Autoencoder, with a Euclidean latent space, is structurally incapable of capturing topological properties of certain datasets.
