Generative Adversarial Networks, or GANs for short are unsupervised learning tasks in machine learning that involve automatically discovering and learning the regularities or patterns in input data in such a way that the model can be used to generate or output new examples that plausibly could have been drawn from the original dataset.
001
The idea for this art piece was to see what an AI model would generate after I fed it with all the pictures I took over the course of a week in Tokyo. These were random snaps from everyday activities, both daytime and nighttime. It was influenced by the people I’ve met, my interactions with them and the decisions we took. You are all co-authors of this piece, you all influenced it in some kind of way, either by a recommendation of a spot we should go to grab a drink, eat gyozas, take a certain route or get out at a certain metro station. These decisions resulted in the memories that I captured on my phone, which were used to train a generative adversarial network (GAN). This machine learning model produced 100 new images based on its interpretation of what the trip was about, and how it perceived these past 8 days.