Understanding Deep Neural Networks via Linear Separability of Hidden Layers

no code implementations • 26 Jul 2023 • Chao Zhang, Xinyu Chen, Wensheng Li, Lixue Liu, Wei Wu, DaCheng Tao

In this paper, we measure the linear separability of hidden layer outputs to study the characteristics of deep neural networks.

AL-iGAN: An Active Learning Framework for Tunnel Geological Reconstruction Based on TBM Operational Data

no code implementations • 2 Dec 2022 • Hao Wang, Lixue Liu, Xueguan Song, Chao Zhang, DaCheng Tao

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 settlement and landslide) and improve the efficiency of construction.

Active Learning Generative Adversarial Network

GAN-MDF: A Method for Multi-fidelity Data Fusion in Digital Twins

no code implementations • 24 Jun 2021 • Lixue Liu, Chao Zhang, DaCheng Tao

Multi-fidelity data fusion (MDF) methods aims to use massive LF samples and small amounts of HF samples to develop an accurate and efficient model for describing the system with a reasonable computation burden.

Generative Adversarial Network