g CINA CONTENC MI CINE SI CENTENI SEE CONDENN DE CRE SU DE QUAENT ME CONNE CUNTUR DEACLETICE (FIUD SEE DED SEE SER SER SER SEENNN SER SER SEENN SER SER SEENDENNENCEN (_DER SER K of my own striking the more than the spirit of the morning of the Professor …

I trained a recurrent neural net with the same parameters as the most recent version of GLOSSATORY on the Gutenberg e-text of the 1811 edition of Francis Grose's Dictionary of the Vulgar Tongue.

The output was even better than I expected. The following excerpts were taken at increasing temperatures (the …

This is the output of the neuralgae algorithm, which visualises a neural net's idea of some image classes and then classifies the result and repeats, looped into a GIF, and it's exactly the sort of fluid morphing between surreal forms I've been trying to get for two years.

Last year I went right over the top for National Novel Generating Month and wrote a dynastic succession simulator and blogged about it at length. Where did I get the time for that, I find myself asking.

This year I made something simpler. Formations is a parody or homage to …

Here are all 1000 classes in the ImageNet challenge, rendered with the Visual Geometry Group's 19-layer neural net, using the same deepdraw technique I used for the thousand faces of CaffeNet. These ones are rendered on random grayscale noise, not my face.

This is the net which the neuralgae Twitter …

Glossatory is a recurrent neural net trained on all of the definitions in the lexical database WordNet. I recently retrained it on a GPU, increasing the number of hidden units to 512 and the layers from 2 to 3. The results are now a lot more grammatical, and there's a …

I was tinkering around trying to get Justin Johnson's neural-style implementation working on the HPC - this is an algorithm which uses a deep learning image recognition net to extract low-level style features from one image and use them to render the large-scale contours of another. This technique has been commercialised …

@voronidols are on Twitter, and also on Mastodon @voronidols@botsin.space and the bots page.

Source code

I found out about NaPoGenMo halfway through April, and decided to do something throwaway and quick for it, unlike my last couple of NaNoGenMo efforts, which have taken much more effort than the end results justified. (I found out about it on Mastodon but that's a story for another blog …

The third of three posts about the details of my NaNoGenMo 2016 project, Annales

1. Vocabularies | 2. TextGen | 3. Events

The event loop is the least interesting part of Annales, but it took the most effort and time. The basic idea is that there's a structured variable which describes the …