Electroencephalography Machine Learning

Goals:

• Improve data augmentation: synthesize EEGs with a forward model enabled recurrent conditional wGAN
• Improve understanding and diagnostics: Create a siamese network capable of generated a manifold of EEGs
• Imporved singal processing: Remove Artifacts from EEGs

TODOS:

• implement progressive gan
• create generations with progressive gan
• add physics models to progressive gan

---

• Test g loss with c and d attributes
• Create forward model enabled generator
• Create conditional generator (concat)
• Create conditional generator (projection)
• Enable larger continuous EEG generation (Add S_t as input)
• Create convolutional varient
• Create remove noise network (conv and recurrent)
• Test different intermediate representations
• Get the entire architecture to compile
• Train Siamese Network
• Use Siamese Network to Generate a manifold
• Use cGAN for data augmentation

Project Plan: