Skip to content

Latest commit

 

History

History
24 lines (16 loc) · 789 Bytes

Assignment5.md

File metadata and controls

24 lines (16 loc) · 789 Bytes

Assignment 5 - COMP 135 – Spring 2016

Due: April 26
Turn in hardcopy in class

Use http://playground.tensorflow.org/ on the two-spirals problem (see Data on left side)

Perturb the following parameters, considering extreme values as well as moderate ones (with respect to the available parameter settings):

  1. Ratio of training to test data
  2. Data noise
  3. Learning rate
  4. Regularization rate and type (L1 or L2)
  5. Number of hidden neurons
  6. Number of hidden layers
  7. Alternative input features

Describe and discuss:

a. Test/training loss (is there overfitting?)

b. Convergence rates (does the network stabilize? how fast?)

c. Output map (what pattern does the network learn? in what ways does it differ from the spirals?) and maps within hidden neurons