13 citations · 19 across the 7 of their papers we have counts for
5 papers · 1 filter
Adaptively Point-weighting Curriculum Learning
Wensheng Li, Yichao Tian, Hao Wang +4
Curriculum learning (CL) mimics human learning, in which easy samples are learned first, followed by harder samples, and has become an effective method for training deep networks.…
Understanding Deep Neural Networks via Linear Separability of Hidden Layers
Chao Zhang, Xinyu Chen, Wensheng Li +3
In this paper, we measure the linear separability of hidden layer outputs to study the characteristics of deep neural networks. In particular, we first propose Minkowski difference…
AL-iGAN: An Active Learning Framework for Tunnel Geological Reconstruction Based on TBM Operational Data
Hao Wang, Lixue Liu, Xueguan Song +2
In tunnel boring machine (TBM) underground projects, an accurate description of the rock-soil types distributed in the tunnel can decrease the construction risk ({\it e.g.} surface…
Revisiting PINNs: Generative Adversarial Physics-informed Neural Networks and Point-weighting Method
Wensheng Li, Chao Zhang, Chuncheng Wang +2
Physics-informed neural networks (PINNs) provide a deep learning framework for numerically solving partial differential equations (PDEs), and have been widely used in a variety of…
GAN-MDF: A Method for Multi-fidelity Data Fusion in Digital Twins
Lixue Liu, Chao Zhang, Dacheng Tao
The Internet of Things (IoT) collects real-time data of physical systems, such as smart factory, intelligent robot and healtcare system, and provide necessary support for digital t…