no code implementations • 27 May 2023 • Yangjie Zhou, Yaoxu Song, Jingwen Leng, Zihan Liu, Weihao Cui, Zhendong Zhang, Cong Guo, Quan Chen, Li Li, Minyi Guo
Graph neural networks (GNNs) are powerful tools for exploring and learning from graph structures and features.
no code implementations • 24 Sep 2021 • Zhendong Zhang
We prove that frequency pooling is shift-equivalent and anti-aliasing based on the property of Fourier transform and Nyquist frequency.
no code implementations • 24 Sep 2021 • Zhendong Zhang
In this paper, we propose a framework of learning multi-layered GBDT via BP.
no code implementations • 25 Sep 2019 • Zhendong Zhang, Cheolkon Jung
Convolutional layer utilizes the shift-equivalent prior of images which makes it a great success for image processing.
3 code implementations • 10 Sep 2019 • Zhendong Zhang, Cheolkon Jung
When there are multiple outputs, GBDT constructs multiple trees corresponding to the output variables.
1 code implementation • 19 Aug 2019 • Zhendong Zhang, Cheolkon Jung, Xiaolong Liang
Recent works show that deep neural networks trained on image classification dataset bias towards textures.
no code implementations • 26 Feb 2019 • Zhendong Zhang, Cheolkon Jung
However, the performance of an RC network is not satisfactory if we directly unroll the same kernels multiple steps.
no code implementations • NIPS Workshop CDNNRIA 2018 • Zhendong Zhang, Cheolkon Jung
RC reduces the redundancy across layers and is complementary to most existing model compression approaches.
no code implementations • ICLR 2018 • Zhendong Zhang, Cheolkon Jung
We define the approximated smoothness as the regularization term.