Itay Hubara
Itay Hubara
Verified email at campus.technion.ac.il
TitleCited byYear
Binarized neural networks: Training deep neural networks with weights and activations constrained to+ 1 or-1
M Courbariaux, I Hubara, D Soudry, R El-Yaniv, Y Bengio
arXiv preprint arXiv:1602.02830, 2016
11432016
Binarized neural networks
I Hubara, M Courbariaux, D Soudry, R El-Yaniv, Y Bengio
Advances in neural information processing systems, 4107-4115, 2016
6302016
Quantized neural networks: Training neural networks with low precision weights and activations
I Hubara, M Courbariaux, D Soudry, R El-Yaniv, Y Bengio
The Journal of Machine Learning Research 18 (1), 6869-6898, 2017
5732017
Train longer, generalize better: closing the generalization gap in large batch training of neural networks
E Hoffer, I Hubara, D Soudry
Advances in Neural Information Processing Systems, 1731-1741, 2017
2182017
Expectation backpropagation: Parameter-free training of multilayer neural networks with continuous or discrete weights
D Soudry, I Hubara, R Meir
Advances in Neural Information Processing Systems, 963-971, 2014
1512014
Scalable methods for 8-bit training of neural networks
R Banner, I Hubara, E Hoffer, D Soudry
Advances in neural information processing systems, 5145-5153, 2018
412018
Fix your classifier: the marginal value of training the last weight layer
E Hoffer, I Hubara, D Soudry
arXiv preprint arXiv:1801.04540, 2018
272018
Deep unsupervised learning through spatial contrasting
E Hoffer, I Hubara, N Ailon
arXiv preprint arXiv:1610.00243, 2016
182016
Playing SNES in the retro learning environment
N Bhonker, S Rozenberg, I Hubara
arXiv preprint arXiv:1611.02205, 2016
152016
Augment your batch: better training with larger batches
E Hoffer, T Ben-Nun, I Hubara, N Giladi, T Hoefler, D Soudry
arXiv preprint arXiv:1901.09335, 2019
72019
Mlperf inference benchmark
VJ Reddi, C Cheng, D Kanter, P Mattson, G Schmuelling, CJ Wu, ...
arXiv preprint arXiv:1911.02549, 2019
52019
Quantized neural network training and inference
ELY Ran, I Hubara, D Soudry
US Patent App. 15/478,531, 2017
42017
Quantized back-propagation: Training binarized neural networks with quantized gradients
I Hubara, E Hoffer, D Soudry
22018
The Knowledge Within: Methods for Data-Free Model Compression
M Haroush, I Hubara, E Hoffer, D Soudry
arXiv preprint arXiv:1912.01274, 2019
12019
Spatial contrasting for deep unsupervised learning
E Hoffer, I Hubara, N Ailon
arXiv preprint arXiv:1611.06996, 2016
12016
Large-scale computations using an adaptive numerical format
I Hubara
US Patent 10,491,239, 2019
2019
MLPerf Inference Benchmark
V Janapa Reddi, C Cheng, D Kanter, P Mattson, G Schmuelling, CJ Wu, ...
arXiv, arXiv: 1911.02549, 2019
2019
Mix & Match: training convnets with mixed image sizes for improved accuracy, speed and scale resiliency
E Hoffer, B Weinstein, I Hubara, T Ben-Nun, T Hoefler, D Soudry
arXiv preprint arXiv:1908.08986, 2019
2019
Deep Learning Algorithm Predicts Endovascular Aortic Aneurysm Repair Same-Day Discharge with Discrimination Equivalent to a Validated Regression Model
DS Zarkowsky, B Nejim, I Hubara, CW Hicks, PP Goodney, JS Hiramoto, ...
Journal of the American College of Surgeons 227 (4), S286, 2018
2018
Binarized Back-Propagation: Training Binarized Neural Networks with Binarized Gradients
I Hubara, E Hoffer, D Soudy
2017
The system can't perform the operation now. Try again later.
Articles 1–20