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

@article{Poltronieri2019TechnicalIA,
  title={Technical Images and Visual Art in the Era of Artificial Intelligence: From GOFAI to GANs},
  author={Fabrizio Augusto Poltronieri and Max H{\"a}nska},
  journal={Proceedings of the 9th International Conference on Digital and Interactive Arts},
  year={2019}
}
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… 

Figures from this paper

Prompt Engineering for Text-Based Generative Art

Text-based generative art has seen an explosion of interest in 2021. Online communities around text-based generative art as a novel digital medium have quickly emerged. This short paper identifies

References

SHOWING 1-10 OF 21 REFERENCES

Progressive Growing of GANs for Improved Quality, Stability, and Variation

TLDR
A new training methodology for generative adversarial networks is described, starting from a low resolution, and adding new layers that model increasingly fine details as training progresses, allowing for images of unprecedented quality.

A Style-Based Generator Architecture for Generative Adversarial Networks

TLDR
An alternative generator architecture for generative adversarial networks is proposed, borrowing from style transfer literature, that improves the state-of-the-art in terms of traditional distribution quality metrics, leads to demonstrably better interpolation properties, and also better disentangles the latent factors of variation.

MidiNet: A Convolutional Generative Adversarial Network for Symbolic-Domain Music Generation

TLDR
This work proposes a novel conditional mechanism to exploit available prior knowledge, so that the model can generate melodies either from scratch, by following a chord sequence, or by conditioning on the melody of previous bars, making it a generative adversarial network (GAN).

Deep Learning

TLDR
Deep learning is making major advances in solving problems that have resisted the best attempts of the artificial intelligence community for many years, and will have many more successes in the near future because it requires very little engineering by hand and can easily take advantage of increases in the amount of available computation and data.

Deep Learning Face Attributes in the Wild

TLDR
A novel deep learning framework for attribute prediction in the wild that cascades two CNNs, LNet and ANet, which are fine-tuned jointly with attribute tags, but pre-trained differently.

Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery

TLDR
AnoGAN, a deep convolutional generative adversarial network is proposed to learn a manifold of normal anatomical variability, accompanying a novel anomaly scoring scheme based on the mapping from image space to a latent space.

What computers still can't do - a critique of artificial reason

TLDR
For this edition of What Computers Can't Do, Hubert Dreyfus has added a lengthy new introduction outlining changes and assessing the paradigms of connectionism and neural networks that have transformed the field.

Philosophy and computing: An introduction

TLDR
For Kurzweil, paradise is only thirty years away when "the basic necessities of food, shelter and security are available for the vast majority of the human population" and, "a variety of neural implant technology has essentially eliminated the handicaps associated with most disabilities" (p.222).

The Challenges of Real-Time All

TLDR
An organizing conceptual structure for current real-time AI research is described, exploring the meanings this term has acquired and some necessary steps for reaching them are specified.