LO2- Generative Art

I really liked Allison Parrish’s Compasses.
http://sync.abue.io/issues/190705ap_sync2_27_compasses.pdf

It “has two parts: a “speller,” which spells words based on how they sound, and a “sounder-out,” which sounds out words based on how they’re spelled. In the process of sounding out a word, the “sounder-out” produces a fixed-length numerical vector, known as a “hidden state,” which is essentially a condensed representation of a word’s phonetics. The “speller” can then use the phonetic information contained in this hidden state to produce a plausible spelling of the word.” (http://portfolio.decontextualize.com/) It really drew my eye on how it’s reproducing what has been produced. I like how it’s poetic and artistic yet very dry at the same time because of its mechanical nature. I have no idea of how she created the algorithm to generate this work, but I guess it’s some kind of machine learning. I liked how she took the multiple layers of the words and regenerate different forms of the words.