Samuel, beat poet

I didn't contribute to NaNoGenMo this year: on the spur of the moment, I decided to try writing 50,000 words of fiction, rather than generating it, and blogged briefly about it at Nannygoat Hill. I didn't even get around to feeding the results into a neural net, like I …

more ...

Sartor Resartus RNN

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 …

more ...


VGG_ILSVRC gif loop

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.

more ...



Glossatory retrained

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 …

more ...



NaPoGenMo 2017

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 …

more ...