compression ratio
649adc59afdef2a8b9e943f94a04b02f-Paper.pdf
But these methods are unable to improve throughput (frames-per-second) on real-life hardware while simultaneously preserving robustness toadversarial perturbations.
- Asia > China > Shanghai > Shanghai (0.04)
- North America > United States > California > Alameda County > Livermore (0.04)
- Europe > United Kingdom > England > Cambridgeshire > Cambridge (0.04)
Andrey Kuzmin, Markus Nagel, Mart van Baalen, Arash Behboodi, Tijmen Blankevoort Qualcomm AI Research
In this paper, we set out to answer the question on which is better: neural network quantization or pruning? By answering this question, we hope to inform design decisions made on neural network hardware going forward. We provide an extensive comparison between the two techniques for compressing deep neural networks.
- Telecommunications (0.41)
- Semiconductors & Electronics (0.41)
- North America > United States > California (0.04)
- Oceania > Australia > New South Wales > Sydney (0.04)
- Africa > Senegal > Kolda Region > Kolda (0.04)
- Information Technology (0.68)
- Government (0.46)
- Information Technology > Artificial Intelligence > Representation & Reasoning (1.00)
- Information Technology > Artificial Intelligence > Natural Language (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (1.00)
- Information Technology > Communications (0.93)
- Research Report > Experimental Study (0.93)
- Research Report > New Finding (0.93)
- Europe (0.14)
- North America > United States > Pennsylvania > Allegheny County > Pittsburgh (0.04)
- North America > United States > Indiana > Marion County > Indianapolis (0.04)
- North America > United States > California (0.04)
- Research Report > Experimental Study (1.00)
- Research Report > New Finding (0.68)
- Law (1.00)
- Government > Regional Government (0.67)
- Information Technology > Security & Privacy (0.46)
Global Sparse Momentum SGD for Pruning Very Deep Neural Networks
Xiaohan Ding, guiguang ding, Xiangxin Zhou, Yuchen Guo, Jungong Han, Ji Liu
DNN pruning is an approach for deep model compression, which aimsateliminating someparameters withtolerable performance degradation.
- Asia > China > Beijing > Beijing (0.05)
- North America > United States > Hawaii > Honolulu County > Honolulu (0.04)
- North America > Canada > British Columbia > Metro Vancouver Regional District > Vancouver (0.04)
- (4 more...)
GradiVeQ: Vector Quantization for Bandwidth-Efficient Gradient Aggregation in Distributed CNN Training
Mingchao Yu, Zhifeng Lin, Krishna Narra, Songze Li, Youjie Li, Nam Sung Kim, Alexander Schwing, Murali Annavaram, Salman Avestimehr
Neural Information Processing Systems http://nips.cc/
- North America > United States > California (0.14)
- North America > United States > Illinois (0.04)
- North America > Canada > Quebec > Montreal (0.04)
- North America > Canada > Ontario > Toronto (0.04)
A Tensorized Transformer for Language Modeling
Xindian Ma, Peng Zhang, Shuai Zhang, Nan Duan, Yuexian Hou, Ming Zhou, Dawei Song
Neural Information Processing Systems http://nips.cc/
- Asia > Myanmar > Tanintharyi Region > Dawei (0.04)
- Asia > China > Beijing > Beijing (0.04)
- Asia > China > Tianjin Province > Tianjin (0.04)
- (2 more...)