Chapter 3: Automating Complicated Model Development with AutoGluon

In Chapter 1, Getting Started with Automated Machine Learning on AWS, you were introduced to the ACME Fishing Logistics use case, where you created a production-grade MLP model using a typical ML process. While the example only highlights a basic artificial neural network architecture, it also provides a suitable introduction to the concept of deep learning.

Deep learning is an advanced ML technique that can be used to solve complex and challenging use cases such as customer sentiment analysis, language translation, and object detection images and videos. These complex use cases often require the ML practitioner to create very intricate, as well as exceptionally large, neural network architectures. Some of these architectures can have hundreds of thousands, even billions, of trainable parameters. The more complicated the network, the more challenging it becomes to train and therefore, the more challenging it becomes...