Deep Learning coding experiment from Michael Flynn explores generating human faces using Deconvolution neural networks:
One of my favorite deep learning papers is Learning to Generate Chairs, Tables, and Cars with Convolutional Networks. It’s a very simple concept – you give the network the parameters of the thing you want to draw and it does it – but it yields an incredibly interesting result. The network seems like it is able to learn concepts about 3D space and the structure of the objects it’s drawing, and because it’s generating images rather than numbers it gives us a better sense about how the network “thinks” as well.
I happened to stumble upon the [Radboud Faces Database][RaDF] some time ago, and wondered if something like this could be used to generate and interpolate between faces as well.
The results are actually pretty exciting!
Michael explores the various processes and their outputs - one of the more interesting avenues is ‘drunk’ mode, where the processing parameters are random, unsuitable to the task yet create fascinating results:
You can find out more (with links to the code) here