2021
← All researchA Systematic Deep Learning Model Selection for P300-Based Brain-Computer Interfaces A Brute-force CNN Model Selection for Accurate Classification of Sensorimotor Rhythms in BCIs Explainable Deep Learning for Brain-Computer Interfaces through Layerwise Relevance Propagation Data Constraints and Performance Optimization for Transformer-based Models in EEG-based Brain-Computer Interfaces: A Survey Bias correction for linear discriminant analysis
Machine Learning for Neural Signals
Model selection, interpretable deep learning, and statistical methods for neural classification.
Our methodological work explores how model architecture, training data, feature representations, and interpretability shape neural signal classification. It includes both deep learning studies and statistical classification methods.
Research questions & methods
- Systematic CNN model selection for P300 and sensorimotor rhythms
- Transformer architectures and data constraints
- Layerwise relevance propagation and bias-corrected classifiers
Selected publications
2020
2023
2024
2021