Gonçalo Mordido


Postdoctoral Fellow, Mila & Polytechnique Montreal

Email: FirstnameLastname [AT] gmail [DOT] com (note: use c instead of ç)


Biography (CV)

I am a postdoctoral fellow at Mila and Polytechnique Montreal working with Prof. Sarath Chandar and Prof. François Leduc-Primeau. My main research is on promoting efficient training and inference of deep neural networks.


  1. G. Mordido, S. Chandar, F. Leduc-Primeau. Sharpness-aware training for accurate inference on noisy DNN accelerators. CoLLAs 2022 workshop & Edge Intelligence workshop 2022.
  2. S. Guiroy, C. Pal, G. Mordido, S. Chandar. Improving meta-learning generalization with activation-based early-stopping. Short version at Montreal AI Symposium 2022. Long version at CoLLAs 2022.
  3. J. Kern, S. Henwood, G. Mordido, E. Dupraz, A. Aissa-El-Bye, Y. Savaria, F. Leduc-Primeau. MemSE: Fast MSE prediction for noisy memristor-based DNN accelerators. AICAS 2022.
  4. Y. Zhang, Y. Savaria, S. Zhao, G. Mordido, M. Sawan, F. Leduc-Primeau. Tiny CNN for seizure prediction in wearable biomedical devices. Short version at Edge Intelligence workshop 2022. Long version at EMBC 2022.
  5. G. Mordido, M. Keirsbilck, A. Keller. Compressing 1D time-channel separable convolutions using sparse random ternary matrices. INTERSPEECH 2021.
  6. G. Mordido, H. Yang, C. Meinel. Evaluating post-training compression in GANs using locality-sensitive hashing. Preprint.
  7. G. Mordido*, J. Niedermeier*, C. Meinel. Assessing image and text generation with topological analysis and fuzzy logic. WACV 2021.
  8. G. Mordido, C. Meinel. Mark-Evaluate: Assessing language generation using population estimation methods. COLING 2020.
  9. J. Sauder*, T. Hu*, X. Che, G. Mordido, H. Yang and C. Meinel. Best student forcing: A simple training mechanism in adversarial language generation. LREC 2020.
  10. G. Mordido, M. Keirsbilck, A. Keller. Monte Carlo gradient quantization. CVPR 2020 EDLCV workshop.
  11. J. Niedermeier*, G. Mordido* and C. Meinel. Improving the evaluation of generative models with fuzzy logic. AAAI 2020 Meta-Eval workshop.
  12. G. Mordido, H. Yang, and C. Meinel. microbatchGAN: Stimulating diversity with multi-adversarial discrimination. WACV 2020.
  13. G. Mordido*, M. Keirsbilck*, A. Keller. Instant quantization of neural networks using Monte Carlo methods. NeurIPS 2019 EMC2 workshop.
  14. J. Sauder, X. Che, G. Mordido, H. Yang and C. Meinel. Pseudo-ground-truth for adversarial text generation using reinforcement learning. NeurIPS 2018 Deep RL workshop.
  15. G. Mordido, H. Yang, and C. Meinel. Dropout-GAN: Learning from a dynamic ensemble of discriminators. KDD 2018 DL'Day.
  16. G. Mordido, J. Magalhaes, and S. Cavaco. Automatic organisation, segmentation, and filtering of user-generated audio content. MMSP 2017.
  17. G. Mordido, J. Magalhaes, and S. Cavaco. Automatic organisation and quality analysis of user-generated content with audio fingerprinting. EUSIPCO 2017.
*equal contribution


  1. A. Keller, G. Mordido, and M. Van keirsbilck. Incorporating a ternary matrix into a neural network. US Patent, 2022.
  2. A. Keller, G. Mordido, N. Gamboa, and M. Van keirsbilck. Representing a neural network utilizing paths within the network to improve a performance of the neural network. US Patent, 2019.