Search Results - "Fan, Feng Lei"

On Interpretability of Artificial Neural Networks: A Survey by Fan, Feng-Lei, Xiong, Jinjun, Li, Mengzhou, Wang, Ge

“…Deep learning as performed by artificial deep neural networks (DNNs) has achieved great successes recently in many important areas that deal with text, images,…”
Get full text

Neural Network Gaussian Processes by Increasing Depth by Zhang, Shao-Qun, Wang, Fei, Fan, Feng-Lei

“…Recent years have witnessed an increasing interest in the correspondence between infinitely wide networks and Gaussian processes. Despite the effectiveness and…”
Get full text

Attention-embedded Quadratic Network (Qttention) for Effective and Interpretable Bearing Fault Diagnosis by Liao, Jing-Xiao, Dong, Hang-Cheng, Sun, Zhi-Qi, Sun, Jinwei, Zhang, Shiping, Fan, Feng-Lei

“…Bearing fault diagnosis is of great importance to decrease the damage risk of rotating machines and further improve economic profits. Recently, machine…”
Get full text

BearingPGA-Net: A Lightweight and Deployable Bearing Fault Diagnosis Network via Decoupled Knowledge Distillation and FPGA Acceleration by Liao, Jing-Xiao, Wei, Sheng-Lai, Xie, Chen-Long, Zeng, Tieyong, Sun, Jinwei, Zhang, Shiping, Zhang, Xiaoge, Fan, Feng-Lei

“…Deep learning has achieved remarkable success in the field of bearing fault diagnosis. However, this success comes with larger models and more complex…”
Get full text

Low-dimensional Manifold Constrained Disentanglement Network for Metal Artifact Reduction by Niu, Chuang, Cong, Wenxiang, Fan, Feng-Lei, Shan, Hongming, Li, Mengzhou, Liang, Jimin, Wang, Ge

“…Deep neural network based methods have achieved promising results for CT metal artifact reduction (MAR), most of which use many synthesized paired images for…”
Get full text

EM Estimation of the X-Ray Spectrum With a Genetically Optimized Step-Wedge Phantom by Li, Mengzhou, Fan, Feng-Lei, Cong, Wenxiang, Wang, Ge

“…The energy spectrum of an X-ray tube plays an important role in computed tomography (CT), and is often estimated from physical measurement of dedicated…”
Get full text

Retinex Image Enhancement Based on Sequential Decomposition With a Plug-and-Play Framework by Wu, Tingting, Wu, Wenna, Yang, Ying, Fan, Feng-Lei, Zeng, Tieyong

“…The Retinex model is one of the most representative and effective methods for low-light image enhancement. However, the Retinex model does not explicitly…”
Get full text

On Expressivity and Trainability of Quadratic Networks by Fan, Feng-Lei, Li, Mengzhou, Wang, Fei, Lai, Rongjie, Wang, Ge

“…Inspired by the diversity of biological neurons, quadratic artificial neurons can play an important role in deep learning models. The type of quadratic neurons…”
Get full text

On a Sparse Shortcut Topology of Artificial Neural Networks by Fan, Feng-Lei, Wang, Dayang, Guo, Hengtao, Zhu, Qikui, Yan, Pingkun, Wang, Ge, Yu, Hengyong

“…In established network architectures, shortcut connections are often used to take the outputs of earlier layers as additional inputs to later layers. Despite…”
Get full text

A characterization of strongly regular graphs in terms of the largest signless Laplacian eigenvalues by Fan, Feng-lei, Weng, Chih-wen

“…Let G be a simple graph of order n with maximum degree Δ. Let λ (resp. μ) denote the maximum number of common neighbors of a pair of adjacent vertices (resp…”
Get full text

Quadratic Neuron-Empowered Heterogeneous Autoencoder for Unsupervised Anomaly Detection by Liao, Jing-Xiao, Hou, Bo-Jian, Dong, Hang-Cheng, Zhang, Hao, Zhang, Xiaoge, Sun, Jinwei, Zhang, Shiping, Fan, Feng-Lei

“…Inspired by the complexity and diversity of biological neurons, a quadratic neuron is proposed to replace the inner product in the current neuron with a…”
Get full text

An Extending Result on Spectral Radius of Bipartite Graphs by Cheng, Yen-Jen, Fan, Feng-lei, Weng, Chih-wen

“…In this paper, we study the spectral radius of bipartite graphs. Let 𝐺 be a bipartite graph with 𝑒 edges without isolated vertices. It was known that the…”
Get full text

Spatial-Frequency Discriminability for Revealing Adversarial Perturbations by Wang, Chao, Qi, Shuren, Huang, Zhiqiu, Zhang, Yushu, Lan, Rushi, Cao, Xiaochun, Fan, Feng-Lei

“…IEEE Transactions on Circuits and Systems for Video Technology, 2024 The vulnerability of deep neural networks to adversarial perturbations has been widely…”
Get full text

Quadratic Neuron-empowered Heterogeneous Autoencoder for Unsupervised Anomaly Detection by Liao, Jing-Xiao, Hou, Bo-Jian, Dong, Hang-Cheng, Zhang, Hao, Zhang, Xiaoge, Sun, Jinwei, Zhang, Shiping, Fan, Feng-Lei

“…Inspired by the complexity and diversity of biological neurons, a quadratic neuron is proposed to replace the inner product in the current neuron with a…”
Get full text

Attention-embedded Quadratic Network (Qttention) for Effective and Interpretable Bearing Fault Diagnosis by Liao, Jing-Xiao, Dong, Hang-Cheng, Sun, Zhi-Qi, Sun, Jinwei, Zhang, Shiping, Fan, Feng-Lei

“…IEEE Transactions on Instrumentation and Measurement, vol. 72, pp. 1-13, 2023 Bearing fault diagnosis is of great importance to decrease the damage risk of…”
Get full text

Spatial-Frequency Discriminability for Revealing Adversarial Perturbations by Wang, Chao, Qi, Shuren, Huang, Zhiqiu, Zhang, Yushu, Lan, Rushi, Cao, Xiaochun, Fan, Feng-Lei

“…The vulnerability of deep neural networks to adversarial perturbations has been widely perceived in the computer vision community. From a security perspective,…”
Get full text

Manifoldron: Direct Space Partition via Manifold Discovery by Wang, Dayang, Fan, Feng-Lei, Hou, Bo-Jian, Zhang, Hao, Jia, Zhen, Zhang, Boce, Lai, Rongjie, Yu, Hengyong, Wang, Fei

“…A neural network (NN) with the widely-used ReLU activation has been shown to partition the sample space into many convex polytopes for prediction. However, the…”
Get full text

EEG-DG: A Multi-Source Domain Generalization Framework for Motor Imagery EEG Classification by Zhong, Xiao-Cong, Wang, Qisong, Liu, Dan, Chen, Zhihuang, Liao, Jing-Xiao, Sun, Jinwei, Zhang, Yudong, Fan, Feng-Lei

“…Motor imagery EEG classification plays a crucial role in non-invasive Brain-Computer Interface (BCI) research. However, the performance of classification is…”
Get full text

Advanced Neural Networks and Their Interpretation by Fan, Feng-Lei

“…Deep learning has recently achieved huge successes in many applications including natural language processing, computer vision, medical imaging, and so on. In…”
Get full text

Spatiotemporal changes of landscape pattern using impervious surface in Guangdong-Hong Kong-Macao Greater Bay Area, China. by Feng, Shan Shan, Fan, Feng Lei

“…Impervious surface is a key indicator for urbanization degree and the quality of urban environment. It is of great ecological significance to study the…”
Get more information