Introduction

In the previous chapter, you learned how to use some TensorFlow resources to aid in development. These included TensorBoard (for visualizing computational graphs), TensorFlow Hub (an online repository for machine learning modules), and Google Colab (an online Python development environment for running code on Google servers). All these resources help machine learning practitioners develop models efficiently.

In this chapter, you will explore how to create ANNs using TensorFlow. You will build ANNs with different architectures to solve regression and classification tasks. Regression tasks aim to predict continuous variables from the input training data, while classification tasks aim to classify the input data into two or more classes. For example, a model to predict whether or not it will rain on a given day is a classification task since the result of the model will be of two classes—rain or no rain. However, a model to predict the amount of rain on a given...