But a VAE is based on probability. I dont see this in the code you provided. A softmax output cannot be interpreted as the uncertainty of a model. You can only achieve this with having a distribution over the weights of a layer. And this is where tf probability comes into place or the monto carlo dropout during inference mechanism that is proven to work.Anyway the methodology you provided looks very interesting. I do not want to offend you by any means.

--

--

--

Machine Learning Engineer / Data Scientist who likes to learn new stuff about AI every day.

Love podcasts or audiobooks? Learn on the go with our new app.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Alex Vaith

Alex Vaith

Machine Learning Engineer / Data Scientist who likes to learn new stuff about AI every day.

More from Medium

the tyranny of unexamined symbols and choosing humanism

Vague Visions (part 1) : A Dark Denial

The Demon Behind Nigeria's Joblessness, By Saidu Ibrahim Emirokpa

Meet a Member: Vinit Nijhawan