Vahid Partovi Nia
Associated member, GERAD

Principal Machine Learning Scientist, Huawei Noah’s Ark Lab, Montréal
Other titles and affiliations
Research Axes
Research Applications
Publications
News
Vahid Partovi Nia won the Best Industrial Paper Award at the 11th International Conference on Pattern Recognition Applications and Methods (ICPRAM) which took place on February 3-5, 2022. This award is given by the Institute for Systems and Technologies of Information, Control and Communication (INSTICC).
The paper, entitled "iRNN: Integer-only Recurrent Neural Network"](https://arxiv.org/abs/2109.09828)", was co-authored with Eyyüb Sari and Vanessa Courville.
Title: Apprentissage basé sur le Qini pour la prédiction de l'effet causal conditionnel
Title: Evaluation of demand forecast models for urban carsharing
Events
Haitham Bou Ammar – Huawei Research London
Ehsan Nezhadarya – LG Electronics
Mehdi Rezagholizadeh – Huawei Noah’s Ark
Cahiers du GERAD
Batch normalization in quantized networks
Implementation of quantized neural networks on computing hardware leads to considerable speed up and memory saving. However, quantized deep networks are diff...
BibTeX referenceRandom bias initialization improves quantized training
Binary neural networks improve computationally efficiency of deep models with a large margin. However, there is still a performance gap between a successful...
BibTeX reference
Training large-scale deep neural networks is a long, time-consuming operation, often requiring many GPUs to accelerate. In large models, the time spent loadi...
BibTeX referencePrizes and awards
ICPRAM 2022 Best Industrial Paper Award
iRNN: Integer-only Recurrent Neural Network (E. Sari, V. Courville and V. Partovi Nia)Supervision


