THE MEDIUM OF COMPLEXITIES, COMMUNICATING HARDER. (detail) ,  2019

THE MEDIUM OF COMPLEXITIES, COMMUNICATING HARDER.(detail), 2019

PROJECT DESCRIPTION 

The Machine is an ongoing project by interdisciplinary artist Colleen McCulla which uses generative adversarial neural networks to explore the boundaries of human and machine visual artistic expression. This project utilizes a human/AI co-creative system to engage in a process of making that explores the potential of machine learning to transform artistic practice. This project and the accompanying thesis research asks if hybrid human/machine practices are necessary for future human artistic practice. It offers a glimpse of a future where human and artificial intelligence creative expression evolve separately and symbiotically. The Machine challenges the viewer to consider who and/or what is capable of visual expression, authorship, and how we consciously choose to participate in shaping our coexistence with the advancing technologies interwoven in our lives.

TECHNOLOGY 

Artificial Intelligence is technology that solves problems by imitating human thought. Machine Learning is a subfield of artificial intelligence where a machine writes its own rules to solve a problem. At the most basic level, The Machine utilizes ML models that learn how to make visual images after it has been trained on a dataset of thousands of my previous artworks. After the model is trained, it is capable of making its own rules to create its own solution to the problem(create an image in my style) and generate art.

This process of making engages in a dialogue between the human artist and a series of trained neural networks through a semi-automated co-creative system. The models are trained on datasets of human created artwork and the ML models learn and create a solution - an emerging aesthetic of algorithmic perfection, a shift in visual culture built on and beyond human creativity.

GENERATIVE ADVERSARIAL NETWORKS 

The Machine uses two different Generative Adversarial Networks to generate artwork using a training dataset of over 2,500 of my original collages. A Generative Adversarial Network simultaneously trains two models; a generative(G) model captures “data distribution” and a discriminator(D) estimates the probability that a sample came from training data rather than G. “The training procedure for G is to maximize the probability of D making a mistake”(Goodfellow, et al). The introduction of a framework that include both the G and D model adds a two-player game component. The concept of two simultaneous models within the network working in this manner is similar to my mental processing that occurs in my own artistic practice. Although I’m not trying to trick myself into thinking that every new a work I create is something that I’ve already made/seen, I am constantly vacillating between judgment and creation to create a “finished” work. 

The first model “pix2pix” uses a Conditional Generative Adversarial Network(cGAN) to learn mapping from an input image to an output image. A trained pix2pix model will generate an output image from any arbitrary input image. This model is especially flexible because various models can be layered, allowing for generated images to become input images for other trained pix2pix models (Isola et al). 

The second model used is a Deep Convolutional Generative Adversarial Networks(DCGANs). DCGANs are unsupervised learning models that learn a hierarchy of representations from objects parts to scenes both in the generator(G) and the discriminator(D). The limitations of the DCGAN and my hardware lays in the image size of 128 X 128 pixels. This is an open source model that is available for use on github (Radford et al). 

Multi-layer Recurrent Neural Network

The Machinifesto text was generated using a multi-layer recurrent neural network that was trained on 750 plain text pages of my writing. These 750 plain text pages included every piece of writing I completed during graduate school where much development and core research occurred on this project, which began as my MFA Thesis.


ColleenMcC_StudentPortraits_OpenStudios_PDembinski-3210.jpg

COLLEEN McCULLA

Colleen McCulla is an interdisciplinary artist working in Chicago, IL. McCulla’s recent work explores hybrid machine learning and human co-creative systems. Additional areas of research include intellectual property law, data science, information visualization, and creative system design.

Colleen holds a BFA from The Cleveland Institute of Art and an MFA from Columbia College Chicago. McCulla is a TEDx speaker who has been featured by MOO at SCOPE ART Miami Beach and nationwide on PBS television. Colleen is also the creator and host of Paper Cuts a video series which explores the medium of collage on YouTube. Colleen has created one collage everyday since 2012 which can be viewed on her Instagram.

For sales inquiries, speaking requests, and access to accompanying research paper please email c@colleenmcculla.com