Skip to content

Latest commit

 

History

History
4 lines (4 loc) · 285 Bytes

README.md

File metadata and controls

4 lines (4 loc) · 285 Bytes

DL_HW1

In this work we implement a LeNet5 network over FashionMNIST dataset. We use (separately) a dropout, weight decay(L2 loss), and batch normalization layers to show their effect on the modle. Convergence graphs in each scenario are calculated for the train and test accuracies.