Problem Set 13
This is to be completed by February 1st, 2018.
* Complete the lesson:
a. Python Data Science Toolbox (Part II)
For a logistic regressor (multiclass ending in softmax) write down the update rules for gradient descent.
For a two layer perceptron ending in softmax with intermediate relu non-linearity write down the update rules for gradient descent.
- Build a two layer perceptron (choose your non-linearity) in numpy for a multi-class classification problem and test it on MNIST.
- Build a MLP in Keras and test it on MNIST.