Machine Learning for Creativity and Design

NeurIPS 2018 Workshop, Montreal, Canada

Saturday December 8ᵗʰ 8:30 — 18:15

NeurIPS 2018 creativity art gallery

Image credit: Mike Tyka's Portraits of Imaginary People from the NeurIPS 2017 creativity art gallery.

Introduction

Over the past few years, generative machine learning and machine creativity have continued grow and attract a wider audience to machine learning. Generative models enable new types of media creation across images, music, and text - including recent advances such as sketch-rnn and the Universal Music Translation Network. This one-day workshop broadly explores issues in the applications of machine learning to creativity and design. We will look at algorithms for generation and creation of new media and new designs, engaging researchers building the next generation of generative models (GANs, RL, etc). We investigate the social and cultural impact of these new models, engaging researchers from HCI/UX communities and those using machine learning to develop new creative tools. In addition to covering the technical advances, we also address the ethical concerns ranging from the use of biased datasets to building tools for better “DeepFakes”. Finally, we’ll hear from some of the artists and musicians who are adopting machine learning including deep learning and reinforcement learning as part of their own artistic process. We aim to balance the technical issues and challenges of applying the latest generative models to creativity and design with philosophical and cultural issues that surround this area of research.

The goal of this workshop is to bring together researchers and creative practitioners interested in advancing art and music generation to present new work, foster collaborations and build networks.

Keynote Speakers

Kenneth Stanley, University of Central Florida

David Ha, Google Brain

Allison Parrish, NYU ITP

Yaroslav Ganin, DeepMind

Yaniv Taigman, Facebook AI Research

Important Dates

28 October 2018: Submission date for papers and art

9 November 2018: Acceptance notification for papers

19 November 2018: Acceptance notification for art

28 November 2018: Deadline for final copy of accepted papers

3–8 December 2018: NeurIPS Conference

8 December 2018: Workshop

Contact

If you have any questions, please contact us at nips2018creativity@gmail.com

Workshop website: https://nips2018creativity.github.io

Schedule

Time Event
8:30 AM Welcome and Introduction
8:45 AM Invited Talk
Kenneth Stanley
9:15 AM Invited Talk
Yaroslav Ganin
9:45 AM Invited Talk
David Ha
10:15 AM AI art gallery overview
Luba Elliott
10:30 AM Art / Coffee Break
11:00 AM Invited Talk
Yaniv Taigman
11:30 AM Performing Structured Improvisations with Pre-existing Generative Musical Models
Pablo Samuel Castro
11:45 AM Legend of Wrong Mountain: Full Generation of Traditional Chinese Opera Using Multiple Machine Learning Algorithms
Lingdon Huang, Giada Sun, Zheng Jiang
12:00 PM Lunch
1:30 PM Poster Session 1 (papers 8-21)
Evan Casey, Colin A Raffel, Jonathan Simon, Billy Li, Rob Saunders, Petra Gemeinboeck, Eunsu Kang, Songwei Ge, Curtis “Fjord” Hawthorne, Anna Huang, Ting-Wei Su, Eric Chu, Memo Akten, Sonam Damani, Khyatti Gupta, Dilpreet Singh, Patrick Hutchings
2:30 PM Invited Talk
Allison Parrish
3:00 PM Art / Coffee Break
3:30 PM TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer
Sheldon Huang, Cem Anil, Xuchan Bao
3:45 PM Infilling Piano performances
Daphne Ippolito
4:00 PM Improvised Robotic Design with Found Objects
Azumi Maekawa
4:15 PM SpaceSheets: Interactive Latent Space Exploration through a Spreadsheet Interface
Tom White
4:30 PM Runway: Adding artificial intelligence capabilities to design and creative platforms
Cristobal Valenzuela, Anastasis Germanidis, Alejandro Matamala
4:45 PM Open Discussion
5:15 PM AI art show
Ziv Epstein, Violet Chaney, Alex Champandard, Gene Kogan, Josh Davis
5:15 PM Poster Session 2 (papers 22-35)
Katy Gero, Aven Zhou, Simiao Yu, Zhengyan Gao, Chris Donahue, Billy Li, Taegyun Kwon, Patrick Hutchings, Charles Martin, Eunsu Kang, Asanobu Kitamoto, Zheng Jiang, Giada Sun, Philipp Schmitt, Maria Attarian, Alex Lamb, Tarin Clanuwat, Mauro Martino, Holly Grimm, Nikolay Jetchev

Accepted Papers

Papers 1-7 will be presented orally. Papers 8-21 will be presented in the first poster session. Papers 22-35 will be presented in the second poster session.

  1. Infilling Piano Performances
    • Daphne Ippolito, Anna Huang, Curtis Hawthorne, Douglas Eck
  2. TimbreTron: A WaveNet(CycleGAN(CQT(Audio))) Pipeline for Musical Timbre Transfer
    • Sicon Huang, Qiyang Li, Cem Anil, Xuchan Bao, Sageev Oore, Roger B. Grosse
  3. Performing Structured Improvisations with Pre-existing Generative Musical Models
    • Pablo Samuel Castro
  4. Improvised Robotic Design with Found Objects
    • Azumi Maekawa, Ayaka Kume, Hironori Yoshida, Jun Hatori, Jason Naradowsky, Shunta Saito
  5. Legend of Wrong Mountain: Full Generation of Traditional Chinese Opera Using Multiple Machine Learning Algorithms
    • Lingdong Huang, Zheng Jiang, Syuan-Cheng Sun, Tong Bai, Eunsu Kang, Barnabas Poczos
  6. SpaceSheets: Interactive Latent Space Exploration through a Spreadsheet Interface
    • Bryan Loh, Tom White
  7. Runway: Adding artificial intelligence capabilities to design and creative platforms
    • Cristobal Valenzuela, Alejandro Matamala, Anastasis Germanidis
  8. Neural Wavetable: a playable wavetable synthesizer using neural networks
    • Lamtharn Hantrakul, Li-Chia Yang
  9. Thinking Between the Lines
    • Evan Casey, Harry Teitelman
  10. Learning a Latent Space of Multitrack Measures
    • Ian Simon, Adam Roberts, Colin Raffel, Jesse Engel, Curtis Hawthorne, Douglas Eck
  11. Entendrepreneur: Generating Humorous Portmanteaus using Word-Embeddings
    • Jonathan A. Simon
  12. Music Theory Inspired Policy Gradient Method for Piano Music Transcription
    • Jucheng Li, Shuhui Qu, Yun Wang, Xinjian Li, Samarjit Das, Florian Metze
  13. Performative Body Mapping: A Creative Robotics Method for Learning Expressive Movement
    • Rob Saunders, Petra Gemeinboeck
  14. Hallucinating Point Cloud Into 3D Sculptural Object
    • Chun-Liang Li, Eunsu Kang, Songwei Ge, Lingyao Zhang, Austin Dill, Manzil Zaheer, Barnabas Poczos
  15. Combining Learned Lyrical Structures and Vocabulary for Improved Lyric Generation
    • Pablo Samuel Castro, Maria Attarian
  16. Transformer-NADE for Piano Performances
    • Curtis Hawthorne, Anna Huang, Daphne Ippolito, Douglas Eck
  17. Generating Images from Audio
    • Chih Wen Lin, Ting-Wei Su
  18. Artistic Influence GAN
    • Eric Chu
  19. Deep Meditations: Controlled navigation of latent space
    • Memo Akten, Rebecca Fiebrink, Mick Grierson
  20. Using AI to Design Stone Jewelry
    • Khyatti Gupta, Sonam Damani, Kedhar Nath Narahari
  21. Art Around You: Playful Exploration of Online Gallery Collections
    • Dilpreet Singh, Patrick Hutchings
  22. Interactive CPPNs in GLSL
    • Xavier Snelgrove, Matthew Tesfaldet
  23. Predictive Musical Interaction with MDRNNs
    • Charles P. Martin, Jim Torresen
  24. Improvising with MANDI the AI Drummer
    • Patrick Hutchings, Toby Gifford
  25. VirtuosoNet: A Hierarchical Attention RNN for Generating Expressive Piano Performance from Music Score
    • Dasaem Jeong, Taegyun Kwon, Juhan Nam
  26. Deep Learning for Classical Japanese Literature
    • Tarin Clanuwat, Mikel Bober-Irizar, Asanobu Kitamoto, Alex Lamb, Kazuaki Yamamoto, David Ha
  27. Transfer Learning for Style-Specific Text Generation
    • Katy Ilonka Gero, Giannis Karamanolakis, Lydia Chilton
  28. Piano Genie
    • Chris Donahue, Ian Simon, Sander Dieleman
  29. The Chair Project: A Case-Study for using Generative Machine Learning as Automatism
    • Philipp Schmitt, Steffen Weiss
  30. Spatial Feature Combination for Generative Creativity: A Case Study of Bionic Design
    • Simiao Yu, Hao Dong, Pan Wang, Chao Wu, Yike Guo
  31. Automatic Illumination Effects for 2D Characters
    • Zhengyan Gao, Taizan Yonetsuji, Tatsuya Takamura, Toru Matsuoka, Jason Naradowsky
  32. Vox2Net: From 3D Shapes to Network Sculpture.
    • Nima Dehmamy, Luca Stornaiuolo, Mauro Martino
  33. Shanshui-DaDA: An Interactive, Generative Approach to Chinese Shanshui Painting
    • Aven Le Zhou, Qiufeng Wang, Cheng-Hung Lo, Kaizhu Huang
  34. Training on Art Composition Attributes to Augment CycleGAN Art Generation
    • Holly Grimm
  35. Copy the Old or Paint Anew? An Adversarial Framework for (non-) Parametric Image Stylization
    • Nikolay Jetchev, Urs Bergmann, Gokhan Yildirim

Organisers

Luba Elliott, AI Curator

Sander Dieleman, DeepMind

Rebecca Fiebrink, Goldsmiths University of London

Adam Roberts, Magenta, Google Brain

Jesse Engel, Magenta, Google Brain

Tom White, Victoria University of Wellington