1 code implementation • 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.
1 code implementation • 9 Nov 2023 • Xiao-Cong Zhong, Qisong Wang, Dan Liu, Zhihuang Chen, Jing-Xiao Liao, Jinwei Sun, Yudong Zhang, Feng-Lei Fan
In this paper, we propose a novel multi-source domain generalization framework called EEG-DG, which leverages multiple source domains with different statistical distributions to build generalizable models on unseen target EEG data.
no code implementations • 30 Oct 2023 • Tingting Wu, Zhiyan Du, Zhi Li, Feng-Lei Fan, Tieyong Zeng
However, we empirically find that VDIP struggles with processing image details and tends to generate suboptimal results when the blur kernel is large.
1 code implementation • 31 Jul 2023 • Jing-Xiao Liao, Sheng-Lai Wei, Chen-Long Xie, Tieyong Zeng, Jinwei Sun, Shiping Zhang, Xiaoge Zhang, Feng-Lei Fan
To the best of our knowledge, this is the first instance of deploying a CNN-based bearing fault diagnosis model on an FPGA.
no code implementations • 16 May 2023 • Feng-Lei Fan, Wei Huang, Xiangru Zhong, Lecheng Ruan, Tieyong Zeng, Huan Xiong, Fei Wang
A ReLU network is a piecewise linear function over polytopes.
1 code implementation • 13 May 2023 • Yiming Cui, Lecheng Ruan, Hang-Cheng Dong, Qiang Li, Zhongming Wu, Tieyong Zeng, Feng-Lei Fan
We prove a theorem to explain why Cloud-RAIN can enjoy reflection symmetry.
no code implementations • 11 May 2023 • Feng-Lei Fan, Ze-Yu Li, Huan Xiong, Tieyong Zeng
Then, we modify the depth separation theory by showing that a shallow network with intra-layer links does not need to go as wide as before to express some hard functions constructed by a deep network.
1 code implementation • 24 Mar 2023 • HUI ZHANG, Xuexin An, Qiang He, YuDong Yao, Yudong Zhang, Feng-Lei Fan, Yueyang Teng
The former informs that nonlinear aggregation of quadratic neurons can amplify useful signals and suppress unwanted noise, thereby facilitating robustness, while the latter reveals that Q-GAT can leverage more features in prediction thanks to the dual attention mechanism, which endows Q-GAT with the ability to confront adversarial perturbation.
1 code implementation • 11 Mar 2023 • Feng-Lei Fan, Hang-Cheng Dong, Zhongming Wu, Lecheng Ruan, Tieyong Zeng, Yiming Cui, Jing-Xiao Liao
In this paper, with theoretical and empirical studies, we show that quadratic networks enjoy parametric efficiency, thereby confirming that the superior performance of quadratic networks is due to the intrinsic expressive capability.
no code implementations • 23 Jan 2023 • Feng-Lei Fan, Yingxin Li, Hanchuan Peng, Tieyong Zeng, Fei Wang
In the human brain, neuronal diversity is an enabling factor for all kinds of biological intelligent behaviors.
no code implementations • 15 Jan 2023 • Ao Chen, Jinghua Zhang, Md Mamunur Rahaman, Hongzan Sun, M. D., Tieyong Zeng, Marcin Grzegorzek, Feng-Lei Fan, Chen Li
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 resolution of the video, and similarity of sperms and impurities.
no code implementations • 11 Oct 2022 • Tingting Wu, Wenna Wu, Ying Yang, Feng-Lei Fan, Tieyong Zeng
In this paper, using a sequential Retinex decomposition strategy, we design a plug-and-play framework based on the Retinex theory for simultaneously image enhancement and noise removal.
1 code implementation • 1 Jun 2022 • Jing-Xiao Liao, Hang-Cheng Dong, Zhi-Qi Sun, Jinwei Sun, Shiping Zhang, Feng-Lei Fan
Bearing fault diagnosis is of great importance to decrease the damage risk of rotating machines and further improve economic profits.
1 code implementation • 2 Apr 2022 • Jing-Xiao Liao, Bo-Jian Hou, Hang-Cheng Dong, Hao Zhang, Xiaoge Zhang, Jinwei Sun, Shiping Zhang, Feng-Lei Fan
Encouraged by this inspiring theoretical result on heterogeneous networks, we directly integrate conventional and quadratic neurons in an autoencoder to make a new type of heterogeneous autoencoders.
2 code implementations • 14 Jan 2022 • Dayang Wang, Feng-Lei Fan, Bo-Jian Hou, Hao Zhang, Zhen Jia, Boce Zhou, Rongjie Lai, Hengyong Yu, Fei Wang
A neural network with the widely-used ReLU activation has been shown to partition the sample space into many convex polytopes for prediction.
1 code implementation • 12 Oct 2021 • Feng-Lei Fan, Mengzhou Li, Fei Wang, Rongjie Lai, Ge Wang
Despite promising results so far achieved by networks of quadratic neurons, there are important issues not well addressed.
1 code implementation • 29 Aug 2021 • Shao-Qun Zhang, Fei Wang, Feng-Lei Fan
Inspired by a width-depth symmetry consideration, we use a shortcut network to show that increasing the depth of a neural network can also give rise to a Gaussian process, which is a valuable addition to the existing theory and contributes to revealing the true picture of deep learning.
no code implementations • 6 Feb 2020 • 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.