no code implementations • 6 Aug 2023 • Wei Miao, Hong Zhao, Tongjia Chen, Wei Huang, Changyan Xiao
Recent stereo matching networks achieves dramatic performance by introducing epipolar line constraint to limit the matching range of dual-view.
1 code implementation • 4 May 2023 • Ruixin Hong, Hongming Zhang, Hong Zhao, Dong Yu, ChangShui Zhang
In this paper, we propose FAME (FAithful question answering with MontE-carlo planning) to answer questions based on faithful reasoning steps.
no code implementations • 28 Feb 2022 • Sihan Feng, Yong Zhang, Fuming Wang, Hong Zhao
We consider weights in pathways that link neurons longitudinally from input neurons to output neurons, or simply weight pathways, as the basic units for understanding a neural network, and decompose a neural network into a series of subnetworks of such weight pathways.
1 code implementation • 24 Dec 2021 • Jiaxing Yan, Hong Zhao, Penghui Bu, YuSheng Jin
Self-supervised learning has shown very promising results for monocular depth estimation.
no code implementations • 28 Sep 2020 • Hong Zhao
It is found that following an appropriate training strategy that monotonously decreases the cost function, the learning machine in different training stage can mimic the system at different parameter set.
no code implementations • 21 Feb 2020 • Xiaowei Xu, Xiangao Jiang, Chunlian Ma, Peng Du, Xukun Li, Shuangzhi Lv, Liang Yu, Yanfei Chen, Junwei Su, Guanjing Lang, Yongtao Li, Hong Zhao, Kaijin Xu, Lingxiang Ruan, Wei Wu
We found that the real time reverse transcription-polymerase chain reaction (RT-PCR) detection of viral RNA from sputum or nasopharyngeal swab has a relatively low positive rate in the early stage to determine COVID-19 (named by the World Health Organization).
no code implementations • 10 May 2019 • Hong Zhao
We present that, instead of establishing the equations of motion, one can model-freely reveal the dynamical properties of a black-box system using a learning machine.
no code implementations • 24 Jul 2017 • Hong Zhao
Trained by a set of input-output responses or a segment of time series of a black system, a learning machine can be served as a copy system to mimic the dynamics of various black systems.
no code implementations • 23 Apr 2017 • Hong Zhao
The principle of learning, the role of the a prior knowledge, the role of neuron bias, and the basis for choosing neural transfer function and cost function, etc., are still far from clear.
no code implementations • 18 Apr 2017 • Rui Gao, Sergiy A. Vorobyov, Hong Zhao
In our approach, we formulate the multi-focus image fusion problem in terms of an analysis sparse model, and simultaneously perform the restoration and fusion of multi-focus images.
no code implementations • 12 Feb 2016 • Hong Zhao
The support vector machine (SVM) is an important class of learning machines for function approach, pattern recognition, and time-serious prediction, etc.
no code implementations • 2 Nov 2013 • Bin Yang, Hong Zhao, William Zhu
First, we investigate some properties of the definable sets with respect to a covering.
no code implementations • 13 Dec 2012 • Hong Zhao, Fan Min, William Zhu
In this paper, we study the cost-sensitive feature selection problem on numerical data with measurement errors, test costs and misclassification costs.
no code implementations • 12 Nov 2012 • Hong Zhao, Fan Min, William Zhu
In this paper, we consider numerical data with measurement errors and study minimal cost feature selection in this model.
no code implementations • 29 Sep 2012 • Hong Zhao, Fan Min, William Zhu
In this paper, we introduce normal distribution measurement errors to covering-based rough set model, and deal with test-cost-sensitive attribute reduction problem in this new model.