Search Results for author:
Found 17 papers, 10 papers with code
EEG-DG: A Multi-Source Domain Generalization Framework for Motor Imagery EEG Classification
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.
VDIP-TGV: Blind Image Deconvolution via Variational Deep Image Prior Empowered by Total Generalized Variation
However, we empirically find that VDIP struggles with processing image details and tends to generate suboptimal results when the blur kernel is large.
BearingPGA-Net: A Lightweight and Deployable Bearing Fault Diagnosis Network via Decoupled Knowledge Distillation and FPGA Acceleration
To the best of our knowledge, this is the first instance of deploying a CNN-based bearing fault diagnosis model on an FPGA.
Deep ReLU Networks Have Surprisingly Simple Polytopes
A ReLU network is a piecewise linear function over polytopes.
Cloud-RAIN: Point Cloud Analysis with Reflectional Invariance
We prove a theorem to explain why Cloud-RAIN can enjoy reflection symmetry.
Rethink Depth Separation with Intra-layer Links
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.
Quadratic Graph Attention Network (Q-GAT) for Robust Construction of Gene Regulatory Networks
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.
One Neuron Saved Is One Neuron Earned: On Parametric Efficiency of Quadratic Networks
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.
Towards NeuroAI: Introducing Neuronal Diversity into Artificial Neural Networks
In the human brain, neuronal diversity is an enabling factor for all kinds of biological intelligent behaviors.
ACTIVE: A Deep Model for Sperm and Impurity Detection in Microscopic Videos
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.
Retinex Image Enhancement Based on Sequential Decomposition With a Plug-and-Play Framework
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.
Attention-embedded Quadratic Network (Qttention) for Effective and Interpretable Bearing Fault Diagnosis
Bearing fault diagnosis is of great importance to decrease the damage risk of rotating machines and further improve economic profits.
Quadratic Neuron-empowered Heterogeneous Autoencoder for Unsupervised Anomaly Detection
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.
Manifoldron: Direct Space Partition via Manifold Discovery
A neural network with the widely-used ReLU activation has been shown to partition the sample space into many convex polytopes for prediction.
On Expressivity and Trainability of Quadratic Networks
Despite promising results so far achieved by networks of quadratic neurons, there are important issues not well addressed.
Neural Network Gaussian Processes by Increasing Depth
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.
Quasi-Equivalence of Width and Depth of Neural Networks
While classic studies proved that wide networks allow universal approximation, recent research and successes of deep learning demonstrate the power of deep networks.
