A5012236685- EEG and Brain-Computer Interfaces
- Blind Source Separation Techniques
- Neural dynamics and brain function
- BIM and Construction Integration
- Anomaly Detection Techniques and Applications
- Advanced Neural Network Applications
- Image and Signal Denoising Methods
- Image Processing Techniques and Applications
- Generative Adversarial Networks and Image Synthesis
- Neural Networks and Applications
- Machine Learning and ELM
City University of Hong Kong
2025
Technical University of Munich
2022
Beijing Institute of Technology
2022
Dataset distillation (DD) methods have demonstrated remarkable performance for neural networks trained with very limited training data. However, a significant challenge arises in the form of architecture overfitting: distilled dataset synthesized by specific network (i.e., network) generates poor when other architectures test networks), especially larger capacity than network. This article introduces series approaches to mitigate this issue. Among them, DropPath renders large model be an...
In this study, generative adversarial networks named SleepGAN are proposed to expand the training set for automatic sleep stage classification tasks by generating both electroencephalogram (EEG) epochs and sequence relationships of stages. order reach high accuracy, most existing methods require substantial amounts data, but obtaining such quantities real EEG is expensive time-consuming. We introduce few-shot learning, which a method GAN using very small data. This paper presents progressive...
Dataset distillation methods have demonstrated remarkable performance for neural networks trained with very limited training data. However, a significant challenge arises in the form of architecture overfitting: distilled data synthesized by specific network (i.e., network) generates poor when other architectures test networks). This paper addresses this issue and proposes series approaches both designs schemes which can be adopted together to boost generalization across different on We...