Allison Parrish is a user on mastodon.social. You can follow them or interact with them if you have an account anywhere in the fediverse. If you don't, you can sign up here.

Allison Parrish @aparrish@mastodon.social

I logged into the everyword twitter account a few weeks back to set up 2fa and didn't realize that the act of adding a number to the account would make twitter believe it had license to start texting me all the time. weirdly the only account it would just send me notifications about was... everywordcup? twitter.com/everywordcup mastodon.social/media/C9ZyVFRE

misread this as "most accurate source of hypothetical weather" mastodon.social/media/5ps1t3R2

excerpt from the beginning of L.M. Montgomery's Anne of the Island after being resized to exactly 50000 words (using scipy.ndimage.zoom on an array of word vectors) mastodon.social/media/HlFIxIlj

amazon's aws product line is remarkable in its needless breadth and in how so many services have overlapping functionality nearly to the point of being duplicates mastodon.social/media/gTBvUY0-

experimenting upscaling text with convolutional neural networks, latest update: I can now pass in random character ngrams and get back seemingly unrelated text that looks... vaguely... estonian? mastodon.social/media/evHdLRSK

visiting someone's campsite who decided to put tom nook behind bars where he belongs
mastodon.social/media/5QILo363

always somewhat surprising to be reminded that ecclesiastes is part of the christian canon
mastodon.social/media/7RjEcR0a

more text super-resolution experiments with neural networks, this time using bigrams instead of words as the underlying unit. (this is after interrupting the training like 5% into the first epoch just to see what it looks like) mastodon.social/media/t7lwrBsV

tbh kinda jealous of the research that these other allison parrishes are doing mastodon.social/media/BKk-Dgx7

putting this neural network through its paces by trying to predict which (actual) words sound most similar to strings of random characters mastodon.social/media/FJ1mHUij

t-sne of the character embedding layer weights from my orthography-to-phonetic-similarity-vector neural network. reading t-snes is like reading tea leaves but there are some interesting and encouraging clusters here (e/a/i, c/k with back vowels o/u, m/w) mastodon.social/media/2TsSccNB

training a neural network to predict phonetic similarity vectors for words based solely on their orthography (i.e., not in cmudict). the neural network is only at about 20% accuracy but the results are already promising! showing the most similar word in cmudict here just as a sanity check... mastodon.social/media/0bYSIQWC (context: github.com/aparrish/phonetic-s)

i can’t stand the single storey a in the ios 11 notes app. what a bizarre and annoying typography design decision. it’s distracting to the point of making the app unusable
mastodon.social/media/Y38NUwtQ

though there is definitely something distinctly cubist about that image and the whole idea of breaking faces down into components, reminds me of mastodon.social/media/SBWVgAk5 wikiart.org/en/pablo-picasso/p