Следене
Kurt Keutzer
Kurt Keutzer
Professor of the Graduate School, EECS, University of California, Berkeley
Потвърден имейл адрес: berkeley.edu - Начална страница
Заглавие
Позовавания
Позовавания
Година
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and< 0.5 MB model size
FN Iandola
arXiv preprint arXiv:1602.07360, 2016
104822016
The landscape of parallel computing research: A view from berkeley
K Asanovic, R Bodik, B Catanzaro, J Gebis, P Husbands, K Keutzer, ...
31532006
Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge
S Bakas, M Reyes, A Jakab, S Bauer, M Rempfler, A Crimi, RT Shinohara, ...
arXiv preprint arXiv:1811.02629, 2018
20622018
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search
B Wu, X Dai, P Zhang, Y Wang, F Sun, Y Wu, Y Tian, P Vajda, Y Jia, ...
arXiv, 2018
15922018
System-level design: Orthogonalization of concerns and platform-based design
K Keutzer, AR Newton, JM Rabaey, A Sangiovanni-Vincentelli
IEEE transactions on computer-aided design of integrated circuits and …, 2000
13622000
A survey of quantization methods for efficient neural network inference
A Gholami, S Kim, Z Dong, Z Yao, MW Mahoney, K Keutzer
Low-Power Computer Vision, 291-326, 2022
12562022
Densenet: Implementing Efficient Convnet Descriptor Pyramids
F Iandola
arXiv preprint arXiv:1404.1869, 2014
11502014
Squeezeseg: Convolutional neural nets with recurrent crf for real-time road-object segmentation from 3d lidar point cloud
B Wu, A Wan, X Yue, K Keutzer
2018 IEEE international conference on robotics and automation (ICRA), 1887-1893, 2018
10762018
Large batch optimization for deep learning: Training bert in 76 minutes
Y You, J Li, S Reddi, J Hseu, S Kumar, S Bhojanapalli, X Song, J Demmel, ...
arXiv preprint arXiv:1904.00962, 2019
10622019
A view of the parallel computing landscape
K Asanovic, R Bodik, J Demmel, T Keaveny, K Keutzer, J Kubiatowicz, ...
Communications of the ACM 52 (10), 56-67, 2009
9732009
DAGON: Technology binding and local optimization by DAG matching
K Keutzer
Proceedings of the 24th ACM/IEEE Design Automation Conference, 341-347, 1987
8041987
Squeezesegv2: Improved model structure and unsupervised domain adaptation for road-object segmentation from a lidar point cloud
B Wu, X Zhou, S Zhao, X Yue, K Keutzer
2019 international conference on robotics and automation (ICRA), 4376-4382, 2019
7892019
Squeezedet: Unified, small, low power fully convolutional neural networks for real-time object detection for autonomous driving
B Wu, F Iandola, PH Jin, K Keutzer
Proceedings of the IEEE conference on computer vision and pattern …, 2017
7722017
Estimation of average switching activity in combinational and sequential circuits
A Ghosh, S Devadas, K Keutzer, J White
7541992
Dense point trajectories by gpu-accelerated large displacement optical flow
N Sundaram, T Brox, K Keutzer
European conference on computer vision, 438-451, 2010
6082010
Visual transformers: Token-based image representation and processing for computer vision
B Wu, C Xu, X Dai, A Wan, P Zhang, Z Yan, M Tomizuka, J Gonzalez, ...
arXiv preprint arXiv:2006.03677, 2020
6032020
Q-bert: Hessian based ultra low precision quantization of bert
S Shen, Z Dong, J Ye, L Ma, Z Yao, A Gholami, MW Mahoney, K Keutzer
Proceedings of the AAAI Conference on Artificial Intelligence 34 (05), 8815-8821, 2020
5922020
ImageNet Training in Minutes
Y You, Z Zhang, CJ Hsieh, J Demmel, K Keutzer
International Conference on Parallel Processing, 1-10, 2018
579*2018
Hawq: Hessian aware quantization of neural networks with mixed-precision
Z Dong, Z Yao, A Gholami, MW Mahoney, K Keutzer
Proceedings of the IEEE/CVF international conference on computer vision, 293-302, 2019
5602019
Fast support vector machine training and classification on graphics processors
B Catanzaro, N Sundaram, K Keutzer
Proceedings of the 25th international conference on Machine learning, 104-111, 2008
5452008
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–20