I'm looking to build from scratch an implementation of the wake-sleep algorithm also known as an unsupervised neural network. I plan on doing this in Python in order to better understand how it works. In order to facilitate my task I was wondering if anyone could point me to an existing implementation of this concept.

As an aside, I also plan to do the same for a Cascade Correlation Neural Network however I had better luck and found this so if anyone has any better suggestions please do let me know.

Guides, Open Source codebases, articles, etc. are all welcomed.


While also looking for an implementation of the wake-sleep algorithm, I found this python notebook.

This is well detailed, documented and uses only Python/Numpy!


I don't know if you are looking for something in a library, but I've found this in a public Github (I've not checked deeply if it fits for you).

I hope that's what you're looking for.

  • $\begingroup$ That's definitely a start thank you! However it seems to build on tensor flow which is something I would like to avoid. $\endgroup$ – Ge0rges Mar 6 at 17:47

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.