Search Results for author:
Found 16 papers, 6 papers with code
Score-Based Data Generation for EEG Spatial Covariance Matrices: Towards Boosting BCI Performance
In order to synthesize these spatial covariance matrices and facilitate future improvements of geometric deep learning classifiers, we propose a generative modeling technique based on state-of-the-art score-based models.
Graph Neural Networks on SPD Manifolds for Motor Imagery Classification: A Perspective from the Time-Frequency Analysis
The motor imagery (MI) classification has been a prominent research topic in brain-computer interfaces based on electroencephalography (EEG).
Tensor-CSPNet: A Novel Geometric Deep Learning Framework for Motor Imagery Classification
The mainstream DL methodology for the MI-EEG classification exploits the temporospatial patterns of EEG signals using convolutional neural networks (CNNs), which have remarkably succeeded in visual images.
Deep Optimal Transport for Domain Adaptation on SPD Manifolds
In recent years, there has been significant interest in solving the domain adaptation (DA) problem on symmetric positive definite (SPD) manifolds within the machine learning community.
Ternary Hashing
This paper proposes a novel ternary hash encoding for learning to hash methods, which provides a principled more efficient coding scheme with performances better than those of the state-of-the-art binary hashing counterparts.
Rethinking Uncertainty in Deep Learning: Whether and How it Improves Robustness
Deep neural networks (DNNs) are known to be prone to adversarial attacks, for which many remedies are proposed.
Survey: Geometric Foundations of Data Reduction
The purpose of this survey is to briefly introduce nonlinear dimensionality reduction (NLDR) in data reduction.
Privacy Threats Against Federated Matrix Factorization
Matrix Factorization has been very successful in practical recommendation applications and e-commerce.
Rethinking Privacy Preserving Deep Learning: How to Evaluate and Thwart Privacy Attacks
This paper investigates capabilities of Privacy-Preserving Deep Learning (PPDL) mechanisms against various forms of privacy attacks.
Privacy-Preserving Technology to Help Millions of People: Federated Prediction Model for Stroke Prevention
It adopts federated averaging during the model training process, without patient data being taken out of the hospitals during the whole process of model training and forecasting.
Federated Transfer Learning for EEG Signal Classification
The success of deep learning (DL) methods in the Brain-Computer Interfaces (BCI) field for classification of electroencephalographic (EEG) recordings has been restricted by the lack of large datasets.
HHHFL: Hierarchical Heterogeneous Horizontal Federated Learning for Electroencephalography
To verify the effectiveness of our approach, we conduct experiments on a real-world EEG dataset, consisting of heterogeneous data collected from diverse devices.
Stochastic Inverse Reinforcement Learning
The goal of the inverse reinforcement learning (IRL) problem is to recover the reward functions from expert demonstrations.
Interaction-aware Kalman Neural Networks for Trajectory Prediction
Forecasting the motion of surrounding obstacles (vehicles, bicycles, pedestrians and etc.)
Robotics I.2.9; I.2.0
Representation Learning for Spatial Graphs
Recently, the topic of graph representation learning has received plenty of attention.
Socially Aware Kalman Neural Networks for Trajectory Prediction
Trajectory prediction is a critical technique in the navigation of robots and autonomous vehicles.
