First Edition

[1] Malmi, E., Takala, P., Toivonen, H., Raiko, T., & Gionis, A. (2016, August). Dopelearning: A computational approach to rap lyrics generation. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 195-204). ACM.

[2] Gatys, L. A., Ecker, A. S., & Bethge, M. (2015). A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576.

[3] Zhang, H., Goodfellow, I., Metaxas, D., & Odena, A. (2018). Self-attention generative adversarial networks.arXiv preprint arXiv:1805.08318.

Artists:

• Petra Ardai (petra@spaceexplorers.nl)
• Rinske Bosma (rinskebosma@gmail.com)

Researchers:

• Dr. Maryam Alimardani (m.alimardani@uvt.nl)
• Dr. Martin Atzm?ller (m.atzmuller@uvt.nl)
• Lisa E. Rombout, M.Sc. (l.e.rombout@uvt.nl)
• Paris Mavromoustakos – Blom, M.Sc. (P.MavromoustakosBlom@uvt.nl)
• Andrius Penkauskas (a.penkauskas@uvt.nl)
• Ecaterina Grigoriev (e.grigoriev@uvt.nl)
• Ngoc N. T. Doan (n.n.t.doan@uvt.nl)
• Our thanks are due to Dr. Paul Vogt, who helped setting up the team in the beginning.

[1] Todd, P. (1989). A Connectionist Approach to Algorithmic Composition. Computer Music Journal, 13(4), 27-43. doi:10.2307/3679551

[2] Mozer, M. C. (1994). Neural network music composition by prediction: Exploring the benefits of psychoacoustic constraints and multi-scale processing. Connection Science, 6(2-3), 247-280.

[3] Eck, D., & Schmidhuber, J. (2002, September). Finding temporal structure in music: Blues improvisation with LSTM recurrent networks. In Proceedings of the 12th IEEE workshop on neural networks for signal processing (pp. 747-756). IEEE.

[4] Bickerman, G., Bosley, S., Swire, P., & Keller, R. M. (2010, January). Learning to Create Jazz Melodies Using Deep Belief Nets. In ICCC (pp. 228-237).

• Wind Chime
• Aeolian harp
• Suikinkutsu
• Musical dice game
• Iannis Xenakis
• Generating Large Images from Latent Vectors
• Experiments with google – Melody mixer
• Experiments with google – Beat blender
• Magenta Tensorflow
  • Github: Magenta – drums model
  • Github: Magenta – melody model
  • Github: Magenta – polyphony model
  • Magenta – musicVAE
  • Magenta – music transformer

• Braidotti, R. & M. Hlavajova (eds.) (2018), Posthuman Glossary. London: Bloomsbury.
• Quinn, B. (2012), Fashion Futures. London: Merrell.
• Ryan, S.E. (2014), Garments of Paradise. Wearable Discourse in the Digital Age. Cambridge Ma., MIT.
• Seymour, S. (2009) Fashionable Technology: The Intersection of Design, Fashion, Science and Technology, Vienna: Springer.
• Smelik, A. (2018),  New Materialism: A Theoretical Framework for Fashion in the Age of Technological Innovation. International Journal of Fashion Studies, 5 (1) pp. 31-52.

[1] Censorship of images in the Soviet Union (Wikipedia)

[2] Where does the term  fake news come from | Fallon, C. (2017) (HuffPost)

[3] Why humans run the world | Harari, Y.N (2015)

[4] Generative adversarial network (Wikipedia)

[5] A Beginner’s Guide to Generative Adversarial Networks (GANs) | Nicholson, C. (Skymind AI wiki)

[6] Generative Adversarial Networks (GANs) for Beginners: Generating Images of Distracted Drivers | Monge, Z. (2019) (Towards Data Science)

[7] Generative Adversarial Networks recover features in astrophysical images of galaxies | Fowler, L. et al. (2017) (space.ml Galaxy GAN)

[8] GILT: Generating Images from Long Text | Bar El, O. et al. (2019)

[9] Sketch-Based 3D Exploration with Stacked Generative Adversarial Networks (github)

[10] Exploring galaxy evolution with generative models | Schawinski, K. et al. (2018)

[1] Original paper
Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D.,
Ozair, S., Courville, A., and Bengio, Y. (2014). Generative adversarial
nets. In Advances in Neural Information Processing Systems (NIPS) 2014,
pages 2672?2680.

[2] DCGAN
Radford, A., Metz, L., and Chintala, S. (2015). Unsupervised
representation learning with deep convolutional generative adversarial
networks. arXiv preprint arXiv:1511.06434.

[3] BigGAN
Brock, A., Donahue, J., & Simonyan, K. (2018). Large scale gan training
for high fidelity natural image synthesis. arXiv preprint
arXiv:1809.11096.

[4] We have used this particular DCGAN for this paper:
Seeliger, K., Güçlü, U., Ambrogioni, L.,Güçlütürk, Y., & van Gerven, M.
A. (2018). Generative adversarial networks for reconstructing natural
images from brain activity. NeuroImage, 181, 775-785.