Skip to content

Latest commit

 

History

History
10 lines (8 loc) · 361 Bytes

File metadata and controls

10 lines (8 loc) · 361 Bytes

Make yourown code for NN including

  • Back-prop
  • feedforward
  • Mini-batch
  • Gradient Descent with Adaptive Learning Rate
  • Gradient Descent with RMSprop, Momentum and Adam optimization methods

Try different learning rate and different optimization techniques and see how affect the training.

Try different batch-size and see how that affect the training.