Documents publiés en "2023"

Cacciola, M., Frangioni, A., Asgharian, M., Ghaffari, A., & Partovi Nia, V. (février 2023). On the convergence of stochastic gradient descent in low-precision number formats [Communication écrite]. 12th International Conference on Pattern Recognition Applications and Methods (ICPRAM 2023), Lisbon, Portugal. Disponible

Li, X., Liu, B., Yang, R. H., Courville, V., Xing, C., & Partovi Nia, V. (octobre 2023). DenseShift : Towards Accurate and Efficient Low-Bit Power-of-Two Quantization [Communication écrite]. International Conference on Computer Vision (ICCV 2023), Paris, France. Lien externe

Li, X., Parazeres, M., Oberman, A. M., Ghaffari, A., Asgharian, M., & Partovi Nia, V. (2023). EuclidNets: An Alternative Operation for Efficient Inference of Deep Learning Models. SN Computer Science, 4(5). Lien externe

Mosleh, A., Tahaei, M. S., Clark, J. J., & Partovi Nia, V. (juin 2023). Towards Low-Cost Learning-based Camera ISP via Unrolled Optimization [Communication écrite]. 20th Conference on Robots and Vision (CRV 2023), Montréal, QC, Canada. Lien externe

Partovi Nia, V., Sari, E., Courville, V., & Asgharian, M. (2023). Training Integer-Only Deep Recurrent Neural Networks. SN Computer Science, 4(5), 16 pages. Lien externe

Tayaranian Hosseini, M., Ghaffari, A., Tahaei, M. S., Rezagholizadeh, M., Asgharian, M., & Partovi Nia, V. (mai 2023). Towards Fine-tuning Pre-trained Language Models with Integer Forward and Backward Propagation [Communication écrite]. Findings of the Association for Computational Linguistics (EACL 2023), Dubrovnik, Croatia. Lien externe