activity
20172022
most citedHow deep learning works --The geometry of deep learning

10 citations · 29 across the 9 of their papers we have counts for

collaborators

11 papers

stat.ML2022

Supervised Homogeneity Fusion: a Combinatorial Approach

Wen Wang, Shihao Wu, Ziwei Zhu +2

Fusing regression coefficients into homogenous groups can unveil those coefficients that share a common value within each group. Such groupwise homogeneity reduces the intrinsic di…

cs.LG20191 cited

Gauge theory and twins paradox of disentangled representations

X. Dong, L. Zhou

Achieving disentangled representations of information is one of the key goals of deep network based machine learning system. Recently there are more discussions on this issue. In t…

cs.LG20193 cited

Understanding over-parameterized deep networks by geometrization

Xiao Dong, Ling Zhou

A complete understanding of the widely used over-parameterized deep networks is a key step for AI. In this work we try to give a geometric picture of over-parameterized deep networ…

cs.LG20197 cited

Geometrization of deep networks for the interpretability of deep learning systems

Xiao Dong, Ling Zhou

How to understand deep learning systems remains an open problem. In this paper we propose that the answer may lie in the geometrization of deep networks. Geometrization is a bridge…

stat.ML2018

Reducing Parameter Space for Neural Network Training

Tong Qin, Ling Zhou, Dongbin Xiu

For neural networks (NNs) with rectified linear unit (ReLU) or binary activation functions, we show that their training can be accomplished in a reduced parameter space. Specifical…

quant-ph2018

Spacetime as the optimal generative network of quantum states: a roadmap to QM=GR?

Xiao Dong, Ling Zhou

The idea that spacetime geometry is built from quantum entanglement has been widely accepted in the last years. But how exactly the geometry is related with quantum states is still…