Tips and Tricks of the Trade

Learning Objectives

By the end of this chapter, you will be able to:

• Create better deep learning models faster with the help of transfer learning
• Utilize and work with better models through the help of separate train, development and test datasets
• Work with real life datasets
• Make use of AutoML to find the most optimal network with little to no work
• Visualize neural network models
• Use training logs better

This final chapter shall describe concepts of transfer learning and show you how to use training logs effectively.