Summary
In this chapter, we learned when and how to use DL to train an ML model on Azure. We used both a compute instance and a GPU cluster from within the Azure Machine Learning service to train a model using Keras and TensorFlow.
First, we found out that DL works very well on highly structured data with non-obvious relationships from the raw input data to the resulting prediction. Good examples include image classification, speech-to-text, and translation. We also saw that DL models are parametric models with a large number of parameters, so we often need a large amount of labeled or augmented input data. In contrast to traditional ML approaches, the extra parameters are used to train a fully end-to-end model, also including feature extraction from the raw input data.
Training a CNN using the Azure Machine Learning service is not difficult. We saw many approaches, from prototyping in Jupyter to augmenting the training data, to running the training on a GPU cluster with autoscaling...