no code implementations • 8 May 2020 • D. T. Braithwaite, M. O'Connor, W. B. Kleijn
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.
no code implementations • 21 Nov 2019 • Guo-Qiang Zhang, Kenta Niwa, W. B. Kleijn
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.
no code implementations • 19 Jul 2018 • D. T. Braithwaite, W. B. Kleijn
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.