In March, we will hear from the artist Scott Eaton and the researcher Andrew Brock, this time at Somerset House. Scott Eaton will talk about his experiments with conditional GANs, while Andrew Brock will discuss BigGAN and the mechanisms behind it.

The event is curated by Luba Elliott and is part of the Creative AI meetup series designed to bring together artists, developers, designers, technologists and industry professionals to discuss the applications of artificial intelligence in the creative industries. To be notified about future events, sign up to the newsletter.

We are very kindly hosted by Somerset House. If you'd like to learn more about their future events, sign up here.

-----------

Scott Eaton, Artist, Designer and Creative Technologist

Body Soup, Deep Draw, and other Fantastical Experiments in Deep Learning

In this visual feast, Scott reviews two years of his experiments with conditional GANs, specifically image-to-image translation networks, in advance of his summer 2019 London exhibition. Showing an eclectic range of successes and failures, Scott recounts his efforts to create artistically controllable neural networks that represent and abstract the human figure.

Scott Eaton is an artist, designer, and creative technologist. He received his master’s degree from the MIT Media Lab and subsequently studied traditional academic drawing and sculpture at the Florence Academy of Art. His work is currently focused on figurative representation and abstraction using deep neural networks. When not drawing, sculpting or orchestrating backpropogation, he consults widely in the entertainment industry; clients include Disney, Pixar, Warner Bros, Industrial Light & Magic, Valve, Sony, Blizzard, and many other animation, game and visual effects studios.

------------

Andrew Brock, PhD student at the Edinburgh Centre for Robotics, Interned at DeepMind

BigGAN and the Latent Space Odyssey

Generative models have begun to climb the walls of the uncanny valley, driven partially by upward scaling and improved diets of ever more data. With an ever-growing set of latent spaceships, the opportunity for creative exploration in the GANdromedan sector has never been higher. In this talk, I'll discuss BigGAN (and the awesome things people have built with it), why I find the science of generative models so fascinating, and some of the mechanisms behind the unique visual aesthetic of these models.

Once a mildew-mannered mechanical engineer, Andy was bitten by a radioactive tensor and doomed to become a machine learning researcher. He is currently doing a PhD somewhere in Scotland

The schedule for the evening will be as follows.

6pm - 7pm Arrive / Networking (there will be a cash bar!)

7pm - 7.10pm Introduction

7.10pm-7.50pm First talk – Scott Eaton

7.50pm-8.30pm Second talk – Andrew Brock

#LDNcreativeAI

@elluba