Exercise

Batch normalizing a familiar model

Remember the digits dataset you trained in the first exercise of this chapter?

A multi-class classification problem that you solved using softmax and 10 neurons in your output layer.

You will now build a new deeper model consisting of 3 hidden layers of 50 neurons each, using batch normalization in between layers. The kernel_initializer parameter is used to initialize weights in a similar way.

Instructions

100 XP

Import BatchNormalization from tensorflow.keras layers.
Build your deep network model, use 50 neurons for each hidden layer adding batch normalization in between layers.
Compile your model with stochastic gradient descent, sgd, as an optimizer.