“It’s like Hinton diagrams, but for the terminal.”

Which of the two matrix representations below would you rather be looking at?

Screenshot from 2014-05-04 01:38:04

Hinton diagrams are often used for visualising the learnt weights of neural networks. I’ve often found myself trying to imagine what the weights look like. And fortunately for me today, I remembered this project by GitHub’s Zach Holman.

Turns out, overriding the way NumPy represents numbers wasn’t too hard, so I hacked myself a cool little solution. The code’s here for the time being, until I spin it off into it’s own little repo.


EDIT: The code is now in my theano_toolkit repository. Check it out!

Also read...

Leave a Reply

Your e-mail address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.