Do Machines speak our Language?
Using a Generative Adversarial Network (GAN) trained on a dataset of 512 fonts (or images thereof), 100 images of fonts were generated. From these 100, 10 were then selected to represent the full range of results. Based on these 10 images, functional fonts were then created in Glyphs. The reference text is a combination of the beginnings of chapters three and four - the letter and the word - from Jost Hochuli's book Detail in Typography, in which he outlines various aspects of typography, including the relationship between letterforms and legibility. Do Androids Dream of Electric Sheep? by Phillip K. Dick as well as Darwin Among the Machines by Samuel Butler served as inspiration for this work.
Machines, of course, do not speak our language, but are trained to decipher it.
But do the machines even understand what they decipher?
Ring Bound Publication, 210 × 297 mm, 27 pages, 22 of which fold out to 420 × 297 mm
Theoretical diploma exploring GAN font creation and Optical Character Recognition / Machine Reading Comprehension technologies.