Zhi-Qin Xu

Dr. Zhi-Qin Xu

orcid

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2020 in Communications in Computational Physics
Verified
Journal Article
Closed access
ZXZhi-Qin Xu
Zhi-Qin Xu
YZYaoyu Zhang
Yaoyu Zhang
TLTao Luo
Tao Luo
YXYanyang Xiao
Yanyang Xiao
ZMZheng Ma
Zheng Ma
Communications in Computational Physics (CiCP) publishes original research and survey papers of high scientific value in computational modeling of physical problems. Results in multi-physics and multi-scale innovative computational methods and modeling in all physical sciences will be featured. CiCP is a refereed, interdisciplinary journal edited by a group of world-wide leading scientists in diverse fields to guarantee its highest standard. The journal is published in a timely fashion in printed and electronic forms.

9 December 2019
Verified
Book Chapter
Closed access
PDF file
ZXZhi-Qin Xu
Zhi-Qin Xu
YZYaoyu Zhang
Yaoyu Zhang
YXYanyang Xiao
Yanyang Xiao

4 September 2024 in Communications on Applied Mathematics and Computation
Verified
Journal Article
Closed access
PDF file
ZXZhi-Qin Xu
Zhi-Qin Xu
YZYaoyu Zhang
Yaoyu Zhang
TLTao Luo
Tao Luo

19 August 2022 in Combustion and Flame
Verified
Journal Article
Closed access
TZTianhan Zhang
Tianhan Zhang
YYYuxiao Yi
Yuxiao Yi
YXYifan Xu
Yifan Xu
ZCZhi X. Chen
Zhi X. Chen
YZYaoyu Zhang
Yaoyu Zhang
ZXZhi-Qin Xu
Zhi-Qin Xu

23 January 2024 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
ZZZhongwang Zhang
Zhongwang Zhang
ZXZhi-Qin Xu
Zhi-Qin Xu
It is important to understand how dropout, a popular regularization method, aids in achieving a good generalization solution during neural network training. In this work, we present a theoretical derivation of an implicit regularization of dropout, which is validated by a series of experiments. Additionally, we numerically study two implications of the implicit regularization, which intuitively rationalizes why dropout helps generalization. First, we find that input weights of hidden neurons tend to condense on isolated orientations trained with dropout. Condensation is a feature in the non-linear learning process, which makes the network less complex. Second, we find that the training with dropout leads to the neural network with a flatter minimum compared with standard gradient descent training, and the implicit regularization is the key to finding flat solutions. Although our theory mainly focuses on dropout used in the last hidden layer, our experiments apply to general dropout in training neural networks. This work points out a distinct characteristic of dropout compared with stochastic gradient descent and serves as an important basis for fully understanding dropout.

29 July 2013 in Physical Review Letters
Verified
Journal Article
Closed access
DZDouglas Zhou
Douglas Zhou
YXYanyang Xiao
Yanyang Xiao
YZYaoyu Zhang
Yaoyu Zhang
ZXZhi-Qin Xu
Zhi-Qin Xu
DCDavid Cai
David Cai
We study the reconstruction of structural connectivity for a general class of pulse-coupled nonlinear networks and show that the reconstruction can be successfully achieved through linear Granger causality (GC) analysis. Using spike-triggered correlation of whitened signals, we obtain a quadratic relationship between GC and the network couplings, thus establishing a direct link between the causal connectivity and the structural connectivity within these networks. Our work may provide insight into the applicability of GC in the study of the function of general nonlinear networks.