Skip to content

Latest commit

 

History

History
32 lines (19 loc) · 659 Bytes

File metadata and controls

32 lines (19 loc) · 659 Bytes

Experiments

Experiment 1:

Check if the bitmaps for the same number of nodes but for different instances give different outputs

Esperiment 2:

Give the neural net some past values and see if it predicts correctly

Experiment 3:

relu vs sigmoid in the first layer

Tasks

Task 1

Modify the distiller class to handle different sets of training data for teacher and student

Only the n_truth has to be replaced in teacher's predictions

Task 2

Train student (onlive vs offline)

Task 3a

Try regularization techniques

Task 3b

Fitting to training data aggresively in online scenario

Task 4

Documentation + cleaning up repo