François Leduc-Primeau
B.Eng., M.Eng., Ph.D.
Associate Professor
Department of Electrical Engineering
Department of Electrical Engineering
Research interests and affiliations
Research interests
Telecommunications, signal processing, error-correction codes, deep neural networks, digital system design, embedded systems
Affiliation(s)
Expertise type(s) (NSERC subjects)
- 2504 Integrated circuits
- 2507 Communications systems
- 2519 Microelectronics
- 2525 Wireless communication systems
- 2701 Computer hardware
- 2702 Computer systems organization
- 2722 VLSI systems
Publications
Recent publications
Journal article
Conference paper
Journal article
Journal article
Kern, J., Henwood, S., Torcato Mordido, G. F., Dupraz, E., Aissa-El-Bey, A., Savaria, Y., & Leduc-Primeau, F. (2024). Fast and Accurate Output Error Estimation for Memristor-Based Deep Neural Networks. IEEE Transactions on Signal Processing, 72, 1205-1218.
Rohman, S. T., & Leduc-Primeau, F. (2024, November). Fast Energy Optimization of On-Chip ECC Memories [Paper]. IEEE Workshop on Signal Processing Systems (SiPS 2024), Cambridge, MA, USA.
El-Sayegh, B., Dumoulin, C., Leduc-Primeau, F., & Sawan, M. (2024). Improving pelvic floor muscle training with AI: a novel quality assessment system for pelvic floor dysfunction. Sensors, 24(21), 6937 (23 pages).
Hojatian, H., Mlika, Z., Nadal, J., Frigon, J.-F., & Leduc-Primeau, F. (2024). Learning energy-efficient transmitter configurations for massive MIMO beamforming. IEEE Transactions on Machine Learning in Communications and Networking, 2, 939-955.
See all publications (64)
Biography
François Leduc-Primeau received the B.Eng. degree in 2007, the M.Eng. degree in 2010, and a Ph.D. degree in 2016, all in the department of Electrical and Computer Engineering of McGill University (Montreal, Canada). From 2016 to 2018, he was a postdoctoral researcher at IMT Atlantique in Brest, France, and then at École de technologie supérieure in Montreal. He has been a professor at Polytechnique Montreal since 2019.
His research interests span digital system design, telecommunications, and machine learning, with applications in next-generation wireless communication systems, energy-efficient artificial intelligence, and low-energy digital communication.
Education
- B.Eng. (McGill University)
- M.Eng. (McGill University)
- Ph.D. (McGill University)
Supervision at Polytechnique
COMPLETED
-
Ph.D. Thesis (3)
- Hojatian, H. (2023). Beamforming Design for Massive MIMO Systems with Deep Neural Networks [Ph.D. thesis, Polytechnique Montréal].
- Kern, J. (2023). Improving the Energy Efficiency for Signal Processing and Machine Learning Algorithms Using Unreliable Memories [Ph.D. thesis, Polytechnique Montréal].
- El Zarif, N. (2021). A Platform for Enhancing the Vision of Patients Suffering from Age-Related Macular Degeneration Disease [Ph.D. thesis, Polytechnique Montréal].
- Hojatian, H. (2023). Beamforming Design for Massive MIMO Systems with Deep Neural Networks [Ph.D. thesis, Polytechnique Montréal].
-
Master's Thesis (7)
- Fournier, Y. (2024). Conception physique d'un processeur vectoriel RISC-V multicoeur avec une technologie avancée [Master's thesis, Polytechnique Montréal].
- Humblet, E. (2024). Verification and Characterization of Multicore Vector Processors Enhanced for Low-precision Convolutional Layers Through FPGA Emulation [Master's thesis, Polytechnique Montréal].
- Rohman, S. T. (2024). Optimisation énergétique efficace des mémoires ECC intégrées sur puce [Master's thesis, Polytechnique Montréal].
- Brown, S. (2023). Activity Reduction and Energy Modeling of Gallager-B LDPC Decoders [Master's thesis, Polytechnique Montréal].
- Chitsaz Zade Allaf, K. (2023). Robust Quantization for Enhanced Energy Efficiency and Bit Error Tolerance in DNNs [Master's thesis, Polytechnique Montréal].
- Ang Houle, L.-N. (2022). Validation et caractérisation d'un décodeur LDPC matériel en sous-alimentation [Master's thesis, Polytechnique Montréal].
- Dermont, D. B. (2022). Single-Min LDPC Offset Optimization Methods [Master's thesis, Polytechnique Montréal].
News about François Leduc-Primeau
Press review about François Leduc-Primeau
February 22, 2024,
Québec Science,
Solutions pour une intelligence artificielle moins énergivore
François Leduc-Primeau, professeur au Département de génie électrique, explique que le développement de nouvelles puces électroniques plus efficaces rend la consommation d’énergie des grands modèles d’IA plus modérée.
