Neural networks : the official journal of the International Neural Network Society

Dual-view global and local category-attentive domain alignment for unsupervised conditional adversarial domain adaptation.

Neural networks : the official journal of the International Neural Network Society Jan 8, 2025

Conditional adversarial domain adaptation (CADA) is one of the most commonly used unsupervised domain adaptation (UDA) methods. CADA introduces multimodal information to the adversarial learning process to align the distributions of the labeled sourc...

Unsupervised Machine Learning Neural Networks, Computer Humans Algorithms

View on PubMed DOI

A Fine-grained Hemispheric Asymmetry Network for accurate and interpretable EEG-based emotion classification.

Neural networks : the official journal of the International Neural Network Society Jan 8, 2025

In this work, we propose a Fine-grained Hemispheric Asymmetry Network (FG-HANet), an end-to-end deep learning model that leverages hemispheric asymmetry features within 2-Hz narrow frequency bands for accurate and interpretable emotion classification...

Humans Functional Laterality Brain Deep Learning Neural Networks, Computer Electroencephalography Emotions

View on PubMed DOI

Improved analysis of supervised learning in the RKHS with random features: Beyond least squares.

Neural networks : the official journal of the International Neural Network Society Jan 8, 2025

We consider kernel-based supervised learning using random Fourier features, focusing on its statistical error bounds and generalization properties with general loss functions. Beyond the least squares loss, existing results only demonstrate worst-cas...

Supervised Machine Learning Fourier Analysis Least-Squares Analysis Humans Algorithms Neural Networks, Computer

View on PubMed DOI

Multi-Scale Pyramid Squeeze Attention Similarity Optimization Classification Neural Network for ERP Detection.

Neural networks : the official journal of the International Neural Network Society Jan 7, 2025

Event-related potentials (ERPs) can reveal brain activity elicited by external stimuli. Innovative methods to decode ERPs could enhance the accuracy of brain-computer interface (BCI) technology and promote the understanding of cognitive processes. Th...

Humans Evoked Potentials Brain Deep Learning Algorithms Electroencephalography Attention Neural Networks, Computer Brain-Computer Interfaces

View on PubMed DOI

Searching to extrapolate embedding for out-of-graph node representation learning.

Neural networks : the official journal of the International Neural Network Society Jan 7, 2025

Out-of-graph node representation learning aims at learning about newly arrived nodes for a dynamic graph. It has wide applications ranging from community detection, recommendation system to malware detection. Although existing methods can be adapted ...

Machine Learning Neural Networks, Computer Algorithms Humans

View on PubMed DOI