249 citations · 434 across the 24 of their papers we have counts for
25 papers
BearingPGA-Net: A Lightweight and Deployable Bearing Fault Diagnosis Network via Decoupled Knowledge Distillation and FPGA Acceleration
Jing-Xiao Liao, Sheng-Lai Wei, Chen-Long Xie +5
Deep learning has achieved remarkable success in the field of bearing fault diagnosis. However, this success comes with larger models and more complex computations, which cannot be…
Deep ReLU Networks Have Surprisingly Simple Polytopes
Feng-Lei Fan, Wei Huang, Xiangru Zhong +4
A ReLU network is a piecewise linear function over polytopes. Figuring out the properties of such polytopes is of fundamental importance for the research and development of neural…
One Neuron Saved Is One Neuron Earned: On Parametric Efficiency of Quadratic Networks
Feng-Lei Fan, Hang-Cheng Dong, Zhongming Wu +4
Inspired by neuronal diversity in the biological neural system, a plethora of studies proposed to design novel types of artificial neurons and introduce neuronal diversity into art…
Quadratic Graph Attention Network (Q-GAT) for Robust Construction of Gene Regulatory Networks
Hui Zhang, Xuexin An, Qiang He +4
Gene regulatory relationships can be abstracted as a gene regulatory network (GRN), which plays a key role in characterizing complex cellular processes and pathways. Recently, grap…
ACTIVE: A Deep Model for Sperm and Impurity Detection in Microscopic Videos
Ao Chen, Jinghua Zhang, Md Mamunur Rahaman +6
The accurate detection of sperms and impurities is a very challenging task, facing problems such as the small size of targets, indefinite target morphologies, low contrast and reso…
Towards NeuroAI: Introducing Neuronal Diversity into Artificial Neural Networks
Feng-Lei Fan, Yingxin Li, Hanchuan Peng +2
Throughout history, the development of artificial intelligence, particularly artificial neural networks, has been open to and constantly inspired by the increasingly deepened under…
Retinex Image Enhancement Based on Sequential Decomposition With a Plug-and-Play Framework
Tingting Wu, Wenna Wu, Ying Yang +2
The Retinex model is one of the most representative and effective methods for low-light image enhancement. However, the Retinex model does not explicitly tackle the noise problem,…
Attention-embedded Quadratic Network (Qttention) for Effective and Interpretable Bearing Fault Diagnosis
Jing-Xiao Liao, Hang-Cheng Dong, Zhi-Qi Sun +3
Bearing fault diagnosis is of great importance to decrease the damage risk of rotating machines and further improve economic profits. Recently, machine learning, represented by dee…
Quadratic Neuron-empowered Heterogeneous Autoencoder for Unsupervised Anomaly Detection
Jing-Xiao Liao, Bo-Jian Hou, Hang-Cheng Dong +5
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 simplified quadratic functi…
CTformer: Convolution-free Token2Token Dilated Vision Transformer for Low-dose CT Denoising
Dayang Wang, Fenglei Fan, Zhan Wu +3
Low-dose computed tomography (LDCT) denoising is an important problem in CT research. Compared to the normal dose CT (NDCT), LDCT images are subjected to severe noise and artifacts…
Manifoldron: Direct Space Partition via Manifold Discovery
Dayang Wang, Feng-Lei Fan, Bo-Jian Hou +6
A neural network with the widely-used ReLU activation has been shown to partition the sample space into many convex polytopes for prediction. However, the parameterized way a neura…
On Expressivity and Trainability of Quadratic Networks
Feng-Lei Fan, Mengzhou Li, Fei Wang +2
Inspired by the diversity of biological neurons, quadratic artificial neurons can play an important role in deep learning models. The type of quadratic neurons of our interest repl…
Suppression of Correlated Noise with Similarity-based Unsupervised Deep Learning
Chuang Niu, Mengzhou Li, Fenglei Fan +4
Image denoising is a prerequisite for downstream tasks in many fields. Low-dose and photon-counting computed tomography (CT) denoising can optimize diagnostic performance at minimi…
Low-dimensional Manifold Constrained Disentanglement Network for Metal Artifact Reduction
Chuang Niu, Wenxiang Cong, Fenglei Fan +4
Deep neural network based methods have achieved promising results for CT metal artifact reduction (MAR), most of which use many synthesized paired images for training. As synthesiz…
Quasi-Equivalence of Width and Depth of Neural Networks
Feng-Lei Fan, Rongjie Lai, Ge Wang
While classic studies proved that wide networks allow universal approximation, recent research and successes of deep learning demonstrate the power of deep networks. Based on a sym…
On Interpretability of Artificial Neural Networks: A Survey
Fenglei Fan, Jinjun Xiong, Mengzhou Li +1
Deep learning as represented by the artificial deep neural networks (DNNs) has achieved great success in many important areas that deal with text, images, videos, graphs, and so on…
Quadratic Autoencoder (Q-AE) for Low-dose CT Denoising
Fenglei Fan, Hongming Shan, Mannudeep K. Kalra +6
Inspired by complexity and diversity of biological neurons, our group proposed quadratic neurons by replacing the inner product in current artificial neurons with a quadratic opera…
Soft Autoencoder and Its Wavelet Adaptation Interpretation
Fenglei Fan, Mengzhou Li, Yueyang Teng +1
Recently, deep learning becomes the main focus of machine learning research and has greatly impacted many important fields. However, deep learning is criticized for lack of interpr…
On a Sparse Shortcut Topology of Artificial Neural Networks
Fenglei Fan, Dayang Wang, Hengtao Guo +4
In established network architectures, shortcut connections are often used to take the outputs of earlier layers as additional inputs to later layers. Despite the extraordinary effe…
Universal Approximation with Quadratic Deep Networks
Fenglei Fan, Jinjun Xiong, Ge Wang
Recently, deep learning has achieved huge successes in many important applications. In our previous studies, we proposed quadratic/second-order neurons and deep quadratic neural ne…
Fuzzy Logic Interpretation of Quadratic Networks
Fenglei Fan, Ge Wang
Over past several years, deep learning has achieved huge successes in various applications. However, such a data-driven approach is often criticized for lack of interpretability. R…
Shamap: Shape-based Manifold Learning
Fenglei Fan, Ziyu Su, Yueyang Teng +1
For manifold learning, it is assumed that high-dimensional sample/data points are embedded on a low-dimensional manifold. Usually, distances among samples are computed to capture a…
Learning from Pseudo-Randomness With an Artificial Neural Network - Does God Play Pseudo-Dice?
Fenglei Fan, Ge Wang
Inspired by the fact that the neural network, as the mainstream for machine learning, has brought successes in many application areas, here we propose to use this approach for deco…
General Backpropagation Algorithm for Training Second-order Neural Networks
Fenglei Fan, Wenxiang Cong, Ge Wang
The artificial neural network is a popular framework in machine learning. To empower individual neurons, we recently suggested that the current type of neurons could be upgraded to…