https://github.com/superbrucejia/eeg-bayesiancnn

This is an EEG Signals Classification based on Bayesian Convolutional Neural Network (Bayesian CNNs) via Variational Inference.
https://github.com/superbrucejia/eeg-bayesiancnn

bayesian bayesian-cnns bayesian-convnets bayesian-inference bayesian-methods eeg eeg-classification eeg-signals eeg-signals-classification pytorch-implementation

Last synced: 12 months ago
JSON representation

This is an EEG Signals Classification based on Bayesian Convolutional Neural Network (Bayesian CNNs) via Variational Inference.

• Host: GitHub
• URL: https://github.com/superbrucejia/eeg-bayesiancnn
• Owner: SuperBruceJia
• License: mit
• Created: 2020-09-12T03:48:39.000Z (almost 6 years ago)
• Default Branch: master
• Last Pushed: 2020-09-12T04:06:17.000Z (almost 6 years ago)
• Last Synced: 2025-04-21T12:44:10.475Z (about 1 year ago)
• Topics: bayesian, bayesian-cnns, bayesian-convnets, bayesian-inference, bayesian-methods, eeg, eeg-classification, eeg-signals, eeg-signals-classification, pytorch-implementation
• Language: Python
• Homepage: https://github.com/SuperBruceJia/EEG-BayesianCNN
• Size: 204 KB
• Stars: 30
• Watchers: 3
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
## BayesianCNN for EEG Signals Classification

This is an EEG Signals Classification based on Bayesian Convolutional Neural Network via Variational Inference.

---------------------------------------------------------------------------------------------------------

## Traditional CNNs VS Bayesian CNNs

### Filter weight distributions in a Bayesian Vs Frequentist approach

![Distribution over weights in a CNN's filter.](BayesCNNwithdist.png)

---------------------------------------------------------------------------------------------------------

### Fully Bayesian perspective of an entire CNN 

![Distributions must be over weights in convolutional layers and weights in fully-connected layers.](CNNwithdist_git.png)

---------------------------------------------------------------------------------------------------------

## License

MIT License