Publications

Lipizzaner framework is the backbone of several research studies about GAN training that have been published in different fora.

Journals and book chapters:

  1. E. Hemberg, J. Toutouh, U. O’Reilly. Spatial Coevolution for Diverse Training of Generative Adversarial Networks. ACM Transactions on Evolutionary Learning and Optimization, pages 25, Springer (Under review).
  2. J. Toutouh, E. Hemberg, U. O’Reilly. Data Dieting in GAN Training. In: Iba H., Noman N. (eds) Deep Neural Evolution. Natural Computing Series. Springer, Singapore. DOI: 10.1007/978-981-15-3685-4_14

Conferences:

  1. M. Esteban, J. Toutouh, S. Nesmachnow. Parallel/distributed generative adversarial neural networks for data augmentation of COVID-19 training images. In the Latin America High Performance Computing Conference (CARLA 2020). (Under review).
  2. J. Toutouh, E. Hemberg, U. O’Reilly. Analyzing the Components of Distributed Coevolutionary GAN Training. In The Sixteenth International Conference on Parallel Problem Solving from Nature (PPSN XVI). pages. 10, 2020. arxiv.org/abs/2008.01124
  3. J. Toutouh, E. Hemberg, U. O’Reilly. Re-purposing Heterogeneous Generative Ensembles with Evolutionary Computation. In Genetic and Evolutionary Computation Conference (GECCO ’20), pages. 10, 2020. DOI: 10.1145/3377930.3390229
  4. E. Perez, S. Nesmachnow, J. Toutouh, E. Hemberg, U. O’Reilly. Parallel/distributed implementation of cellular training for generative adversarial neural networks. In 10th IEEE Workshop Parallel/Distributed Combinatorics and Optimization (PDCO 2020), pages 7, 2020.DOI: 10.1109/IPDPSW50202.2020.00092
  5. Jamal Toutouh, Erik Hemberg, and Una-May O’Reilly. Spatial Evolutionary Generative Adversarial Networks. In Genetic and Evolutionary Computation Conference (GECCO ’19), July 13–17, 2019, Prague, Czech Republic. ACM, New York, NY, USA, 9 pages. https://doi.org/10.1145/3321707.3321860
  6. A. Al-Dujaili, T. Schmiedlechner, E. Hemberg, U. O’Reilly. Towards distributed coevolutionary GANs. In AAAI 2018 Fall Symposium, 2018.
  7. T. Schmiedlechner, I. Ng Zhi Yong, A. Al-Dujaili, E. Hemberg, U. O’Reilly. Lipizzaner: A System That Scales Robust Generative Adversarial Network Training. In NeurIPS 2018 Workshop on System for Machine Learning, 2018.

Posters:

  1. A System that Scales Robust Generative Adversarial Network Training presented in the MIT College of Computing poster session 2019.
  2. Mustangs: Robust Training of Generative Adversarial Networks by Fostering Diversity presented in the MIT-IBM Watson AI Lab networking and poster reception 2019.
  3. Coevolutionary GANs Training to Foster Diversity presented in the GANocracy: Democratizing GANs 2019.

Tutorials and invited talks:

  1. Lipizzaner: Distributed Coevolution for Resilient Generative Adversarial Networks (GAN) Training, Jamal Toutouh, Universidad de la Republica, Montevideo Uruguay, April 2020.
  2. Deep Neuroevolution applied to Generative Adversarial Networks, Jamal Toutouh, Spain AI, April 2020.
  3. Spatial Coevolutionary Deep Neural Networks Training. Jamal Toutouh. Universidad de la Republica, Montevideo Uruguay, May 2019.