On the Universal Approximability and Complexity Bounds of Quantized ReLU
Neural Networks

On the Universal Approximability and Complexity Bounds of Quantized ReLU Neural Networks

10 February 2018

Jinjun Xiong

Papers citing "On the Universal Approximability and Complexity Bounds of Quantized ReLU Neural Networks"

6 / 6 papers shown

Title
Seeking Interpretability and Explainability in Binary Activated Neural Networks Benjamin Leblanc Pascal Germain FAtt 31 1 0 07 Sep 2022
Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks Kaiqi Zhang Ming Yin Yu-Xiang Wang MQ 16 4 0 13 Jun 2022
Dynamic Group Convolution for Accelerating Convolutional Neural Networks Z. Su Linpu Fang Wenxiong Kang D. Hu M. Pietikäinen Li Liu 6 44 0 08 Jul 2020
The universal approximation power of finite-width deep ReLU networks Dmytro Perekrestenko Philipp Grohs Dennis Elbrächter Helmut Bölcskei 11 36 0 05 Jun 2018
PBGen: Partial Binarization of Deconvolution-Based Generators for Edge Intelligence Jinglan Liu Jiaxin Zhang Yukun Ding Xiaowei Xu Meng-Long Jiang Yiyu Shi 33 4 0 26 Feb 2018
Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights Aojun Zhou Anbang Yao Yiwen Guo Lin Xu Yurong Chen MQ 316 1,047 0 10 Feb 2017