Search Results for author:
Found 3 papers, 0 papers with code
Variance Constrained Autoencoding
However, we show that for stochastic encoders, simultaneously attempting to enforce a distribution constraint and minimising an output distortion leads to a reduction in generative and reconstruction quality.
Approximated Orthonormal Normalisation in Training Neural Networks
Considering a weight matrix W from a particular neural layer in the model, our objective is to design a function h(W) such that its row vectors are approximately orthogonal to each other while allowing the DNN model to fit the training data sufficiently accurate.
Bounded Information Rate Variational Autoencoders
The new constraint subsumes the mutual information between the input and latent variables, combining naturally with the likelihood objective of the observed data as used in a conventional VAE.
