MNIST-Logistic-Regression-MLP-CNN

Logistic regression, MLP with 1 hidden layer and CNN on both MNIST and USPS

Basic requirements:

Logistic regression, MLP with 1 hidden layer and CNN on both MNIST and USPS using a publicly available library (such as tensorflow, ….) are required. No need to tune hyper parameters for CNN. Implementation of back propagation is not required. However, implementing back propagation yourself independently can get you bonus points (up to an extra 10%). If you choose to do this extra, submit code in another separate file proj3code_bp.zip

Bayesian logistic regression:

Implementing Bayesian logistic regression is not required. If you can implement it independently, you can get a huge bonus (up to an extra 50%, since it has never been implemented before). To earn this bonus, you will

agree to give a presentation and do a demo in class. If you choose to do this extra, submit code in another separate file proj3code_bayesian.zip.

Variational logistic regression:

Implementing Variational logistic regression is not required. If you can implement it independently, you can get a huge bonus (up to an extra 50%, since it has never been implemented before). To earn this bonus, you will

agree to give a presentation and do a demo in class. If you choose to do this extra, submit code in another separate file proj3code_variational.zip