Nagel, Markus

Data-Free Quantization Through Weight Equalization and Bias Correction

Nagel, M., Baalen, M. V., Blankevoort, T., & Welling, M. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV)

Advanced Neural Network ApplicationsDomain Adaptation and Few-Shot Learning

Cited by 500

A White Paper on Neural Network Quantization

Nagel, M., Fournarakis, M., Amjad, R. A., Bondarenko, Y., van Baalen, M., & Blankevoort, T. (2021) · arXiv

Advanced Neural Network ApplicationsLow-power high-performance VLSI design

Cited by 323

Up or Down? Adaptive Rounding for Post-Training Quantization

Nagel, M., Amjad, R. A., van Baalen, M., Louizos, C., & Blankevoort, T. (2020) · arXiv

Advanced Neural Network ApplicationsDomain Adaptation and Few-Shot Learning

Cited by 252

LSQ+: Improving low-bit quantization through learnable offsets and better initialization

Bhalgat, Y., Lee, J., Nagel, M., Blankevoort, T., & Kwak, N. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

Advanced Neural Network ApplicationsLow-power high-performance VLSI design

Cited by 236

Pruning vs Quantization: Which is Better?

Kuzmin, A., Nagel, M., Baalen, M. V., Behboodi, A., & Blankevoort, T. (2023) · Advances in Neural Information Processing Systems 36

Advanced Neural Network ApplicationsMachine Learning and Data Classification

Cited by 58

FP8 Quantization: The Power of the Exponent

Kuzmin, A., Van Baalen, M., Ren, Y., Nagel, M., Peters, J., & Blankevoort, T. (2022) · arXiv

Numerical Methods and AlgorithmsLow-power high-performance VLSI design

Cited by 24

FP8 versus INT8 for efficient deep learning inference

van Baalen, M., Kuzmin, A., Nair, S. S., Ren, Y., Mahurin, E., Patel, C., Subramanian, S., Lee, S., Nagel, M., Soriaga, J., et al. (2023) · arXiv

Advanced Neural Network ApplicationsNumerical Methods and Algorithms

Cited by 24