LightNN: Filling the Gap between Conventional Deep Neural Networks and Binarized Networks

2 December 2017

Papers citing "LightNN: Filling the Gap between Conventional Deep Neural Networks and Binarized Networks"

6 / 6 papers shown

Title
A Survey of Methods for Low-Power Deep Learning and Computer Vision Abhinav Goel Caleb Tung Yung-Hsiang Lu George K. Thiruvathukal VLM 12 92 0 24 Mar 2020
PoPS: Policy Pruning and Shrinking for Deep Reinforcement Learning Dor Livne Kobi Cohen 29 50 0 14 Jan 2020
Impact of Low-bitwidth Quantization on the Adversarial Robustness for Embedded Neural Networks Rémi Bernhard Pierre-Alain Moëllic J. Dutertre AAML MQ 24 18 0 27 Sep 2019
ViP: Virtual Pooling for Accelerating CNN-based Image Classification and Object Detection Zhuo Chen Jiyuan Zhang Ruizhou Ding Diana Marculescu 13 12 0 19 Jun 2019
Low-Power Computer Vision: Status, Challenges, Opportunities S. Alyamkin M. Ardi Alexander C. Berg Achille Brighton Bo Chen ... George K. Thiruvathukal Baiwu Zhang Jingchi Zhang Xiaopeng Zhang Shaojie Zhuo 23 10 0 15 Apr 2019
Hardware-Aware Machine Learning: Modeling and Optimization Diana Marculescu Dimitrios Stamoulis E. Cai 16 45 0 14 Sep 2018