Technical Images and Visual Art in the Era of Artificial Intelligence: From GOFAI to GANs

ZotWeb	paper-conference
Src Url	Poltronieri, Hanska (2019)

Abstract

Artificial Intelligence (AI) and art share a common past, where artists employed AI algorithms to generate art. This paper explores the early days of AI-generated images, using Harold Cohen's AARON software as a paradigm of symbolic AI creative systems, and contextualizes the use of modern neural network technologies to create visual artworks. It discusses the methodologies and strategies used to make art using AI in the 1960s, comparing them to new AI algorithms. The discussion focuses on GOFAI (Good Old Fashioned Artificial Intelligence) and GANs (Generative Adversarial Networks) as the main technologies used in distinct historical periods to generate images. Vilém Flusser's conception of technical images provides a conceptual framework for examining the qualities and attributes of AI-generated images.

---

Annotations

Technical Images and Visual Art in the Era of Artificial Intelligence

From GOFAI to GANs

Citer: (Poltronieri & Hänska, 2019)

FTag: Poltronieri-et-Hanska-2019

APA7: Poltronieri, F. A., & Hänska, M. (2019). Technical Images and Visual Art in the Era of Artificial Intelligence: From GOFAI to GANs. Proceedings of the 9th International Conference on Digital and Interactive Arts, 1–8. https://doi.org/10.1145/3359852.3359865

AI creative systems, and contextualizes the use of modern neural net work technologies to create visual artworks. It discusses the methodologies and strategies used to make art using AI in the 1960s, comparing them to new AI algorithms.

GOFAI (Good Old Fashioned Artificial Intelligence)

AIConcept

GANs (Generative Adversarial Networks)

AIConcept

[...] the new NVIDIA Style Gan takes 41 days to train using the Flickr -Faces -HQ (FFHQ ) dataset — a high -quality 70k images dataset of human faces — at 1024x1024 resolution using one Tesla V100 GPU and six days to train the same dataset and resolution using eight Tesla V100 GPUs in paralle
AITraining

[1] Fabrizio Poltronieri, Alex H eilmair . 2013. Der Zufall und die Symmetriebrechung der synthetischen Bilder . In Michael Hanke, Steffi Winkler . Vom Begri ff zum Bild: Medienkultur nach Vilém Flusser , Tectum Wissenscha ft sverlag, Berlin .

[2] Fabrizio Poltronieri . 2018. Visual Th eogonies: Ch ance, control and automation in algorithmic art . Journal of Gaming & Virtual Worlds , 3 (Oct. 2018), 287 – 293. h tt ps://doi.org/ 10.1386/jgvw.10.3.287_3 . [3] Fabrizio Poltronieri . 2014. Communicology, appatatus, and Post - history:Vilém Flusser’s concepts applied to video game s and gami fi cation . In Mathias Fuchs et al . Rethinking Gami fi cation , meson press , Lüneburg .
ConceptLadderOfAbstraction

Figure 1:The Flusserian Ladder of Abstraction. Starting from the concrete world, there follows a negative sequence of abstraction where one reaches a peak, represented by dimensionless calculations that form the synthetic images.

---

---