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 …

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 …

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 …

I've been playing around with the neural net behind @GLOSSATORY as part of this year's NaNoGenMo: here's a preview.

ABDOMINABLE: a small wall of muskeled for swinging in star or supported in the northwestern central England on the Russian Canamaaceae

ABILITY: the quality of being laws and property

ABNORAL: a …

I made a subdomain for my Twitter bots, with a page of info and credits about each of them: bots.mikelynch.org

I made a new bot, @GLOSSATORY, by training a recurrent neural network on a very long list of word definitions from WordNet. The results are quite weird and entertaining if you like this sort of thing:

Tweets by @glossatory

I've updated the algorithm behind neuralgae. It's still the same basic principle: render a deepdraw image based on some random categories, feed the results back through the classifier, and then repeat with the new categories. But the draw part of the cycle now uses the weights from the classification stage …

In 2013 I wrote and published an eighty-one-verse poem in Spenserian stanzas on FSVO. It started as an affectionate parody of the works of writers like Erasmus Darwin, who in the eighteenth century enthusiastically boosted the natural sciences in poems which are now long unread. It grew into something a …

I've made my first Twitter bot. It posts a new image and accompanying text from my Neuralgae NaNoGenMo project, six times a day, modified slightly so that it fits within the character limit. One of my goals with Neuralgae was to generate something which was in some sense readable, and …