BCI Signal Processing: From EEG to Decoding
8-module course on BCI signal processing — EEG acquisition, filtering, feature extraction, and neural decoding.
Key Highlights
- ✓ 8 modules with Python labs
- ✓ EEG signal acquisition and hardware
- ✓ Preprocessing and artifact removal
- ✓ Feature extraction (CSP, wavelets)
- ✓ Deep learning for neural decoding
- ✓ Capstone: build a motor imagery BCI
Overview
An 8-module course on BCI signal processing. Covers EEG acquisition, preprocessing, feature extraction, classification, and neural decoding with deep learning.
What's Inside
Course Modules
(1) Neural Signals Overview, (2) EEG Hardware and Acquisition, (3) Preprocessing and Filtering, (4) Artifact Removal, (5) Feature Extraction, (6) Classical Classifiers, (7) Deep Learning Decoding, (8) Real-Time BCI Systems.
Practical Work
Students use MNE-Python for EEG processing, OpenBCI hardware for acquisition, and PyTorch for deep learning models. The capstone builds a real-time motor imagery classifier.
Ready to dive in?
Explore this resource and discover more across our 12 technology frontiers.