Home / ATypI All Over 2020

Explorations in Machine Learning and Latent Space Type Design

Technology has always been a driver of creative exploration and innovations. As designers, we are currently living in one of the most exciting eras where technology machine learning and artificial intelligence are making enormous leaps forward opening up new exciting avenues. In this project, we wanted to explore the latent space between common typographic defined styles to see what was hidden in between. The hidden space has a structure that can be examined by interpolating between points, and performing vector arithmetic between points in latent space. This has a meaningful and targeted impact on the generated letterforms. We used generative adversarial networks, or GANs, which are trained on raster renderings of glyphs that are added to the architecture for training neural networks for generating images. The project has led to funding by Enterprise Ireland to explore the creation of variable fonts based on the outcomes of the project. It has had a massive impact since posted online. garnering over 40,000 impressions. While type designers denote abstractions in the stroke weight similar to that of a calligraphic pen, the GAN looks at the spaces in between to create new moments and explorations of the type. These are both hypnotising to watch and groundbreaking in terms of form.


Leon Butler

Leon Butler has experience in numerous areas of visual narrative design. Butler has received awards from the Type Directors Club in New York for his work on Generative Typography, is listed as a one of the future makers for 2016, and for the young directors award in 2017. Butler is currently a lecturer at Yeats Academy of Art, Design and Architecture, and continues to grow his own practice—Bold Visual Narrative.