Use these additional exercises to assist in your learning and test your knowledge further.
Answer the following questions:
- Name three different activation functions. Remember, Google is your friend.
- What is the purpose of a bias?
- What would you expect to happen if you reduced the number of epochs in one of the chapter samples? Did you try it?
- What is the purpose of backpropagation?
- Explain the purpose of the Cost function.
- What happens when you increase or decrease the number of encoding dimensions in the Keras autoencoder example?
- What is the name of the layer type that we feed input into?
- What happens when you increase or decrease the batch size?
- What is the shape of the input Tensor for the Keras example? Hint: we already have a print statement displaying this.
- In the last exercise, how many MNIST samples do we train and test with?
As we progress in the book,...
