no code implementations • 3 May 2024 • Feng-Lei Fan, Meng Wang, Hang-Cheng Dong, Jianwei Ma, Tieyong Zeng
First, symbolic regression is used to identify optimal formulas that fit input data by utilizing base functions such as logarithmic, trigonometric, and exponential functions.
no code implementations • 16 Aug 2022 • Kun Qiu, Harry Chang, Ying Wang, Xiahui Yu, Wenjun Zhu, Yingqi Liu, Jianwei Ma, Weigang Li, Xiaobo Liu, Shuo Dai
Sophisticated traffic analytics, such as the encrypted traffic analytics and unknown malware detection, emphasizes the need for advanced methods to analyze the network traffic.
no code implementations • 16 Aug 2022 • Yanqi Wu, Hossein S. Aghamiry, Stephane Operto, Jianwei Ma
We first illustrate that non-smooth velocity models lead to inaccurate wavefields when no boundary conditions are implemented in the loss function.
no code implementations • 23 Sep 2021 • Fangshu Yang, Jianwei Ma
Seismic full waveform inversion (FWI) is a powerful geophysical imaging technique that produces high-resolution subsurface models by iteratively minimizing the misfit between the simulated and observed seismograms.
no code implementations • 24 Sep 2020 • Fangshu Yang, Thanh-an Pham, Nathalie Brandenberg, Matthias P. Lutolf, Jianwei Ma, Michael Unser
Our work paves the way to reliable phase imaging of thick and complex samples with QPI.
no code implementations • 13 Jul 2020 • Siwei Yu, Jianwei Ma
In this article, we review the basic concepts of and recent advances in data-driven approaches from dictionary learning to deep learning in a variety of geophysical scenarios.
1 code implementation • 27 Feb 2019 • Hao Zhang, Xiuyan Yang, Jianwei Ma
We propose a convolutional neural network (CNN) denoising based method for seismic data interpolation.
1 code implementation • 17 Feb 2019 • Fangshu Yang, Jianwei Ma
Seismic velocity is one of the most important parameters used in seismic exploration.
1 code implementation • 27 Oct 2018 • Siwei Yu, Jianwei Ma, Wenlong Wang
We use a convolutional neural network as the basic tool for deep learning.
no code implementations • 7 Oct 2018 • Hao Zhang, Jianwei Ma
In most convolution neural networks (CNNs), downsampling hidden layers is adopted for increasing computation efficiency and the receptive field size.
2 code implementations • 3 Oct 2018 • Florian Boßmann, Jianwei Ma
In this work we introduce a generalization using shifted rank-1 matrices to approximate $A\in\mathbb{C}^{M\times N}$.
Numerical Analysis Numerical Analysis