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 ...




Annales: Details

This was the first time I submitted a NaNoGenMo entry which aimed at being readable, in contrast to my previous efforts, Everywhere Dense and Neuralgae, which were really abstract. Annales is a generated parody of a very ancient genre, the chronicle, which tells history as a sequence of reigns, deaths …

more ...


A bit of a flutter

I went off Nate Silver a bit when I read The Signal and the Noise because I thought he was a bit scanty in explaining Bayesian analysis but mostly because he goes on about how true Bayesians should be prepared to back up their assessments of probabilities with a wager …

more ...