Prati
Marios Fournarakis
Marios Fournarakis
Rain Neuromorphics
Potvrđena adresa e-pošte na rain.ai
Naslov
Citirano
Citirano
Godina
A white paper on neural network quantization
M Nagel, M Fournarakis, RA Amjad, Y Bondarenko, M Van Baalen, ...
arXiv preprint arXiv:2106.08295, 2021
3172021
Overcoming oscillations in quantization-aware training
M Nagel, M Fournarakis, Y Bondarenko, T Blankevoort
International Conference on Machine Learning, 16318-16330, 2022
482022
Neural network quantization with ai model efficiency toolkit (aimet)
S Siddegowda, M Fournarakis, M Nagel, T Blankevoort, C Patel, ...
arXiv preprint arXiv:2201.08442, 2022
242022
In-hindsight quantization range estimation for quantized training
M Fournarakis, M Nagel
Proceedings of the IEEE/CVF conference on computer vision and pattern …, 2021
62021
Quantization robust federated learning for efficient inference on heterogeneous devices
K Gupta, M Fournarakis, M Reisser, C Louizos, M Nagel
arXiv preprint arXiv:2206.10844, 2022
52022
Softmax bias correction for quantized generative models
NP Pandey, M Fournarakis, C Patel, M Nagel
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023
32023
QBitOpt: Fast and Accurate Bitwidth Reallocation during Training
J Peters, M Fournarakis, M Nagel, M Van Baalen, T Blankevoort
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2023
12023
Quantizing Neural Networks for Low-Power Computer Vision
M Fournarakis, M Nagel, RA Amjad, Y Bondarenko, M van Baalen, ...
Low-Power Computer Vision, 235-272, 2022
2022
Sustav trenutno ne može provesti ovu radnju. Pokušajte ponovo kasnije.
Članci 1–8