Linear Regression with TensorFlow
In this chapter, we will cover the concept of linear regression and how we can implement it using TensorFlow. We will start by discussing what linear regression is, how it works, its underlying assumptions, and the type of problems that can be solved using it. Next, we will examine the various evaluation metrics used in regression modeling, such as mean squared error, mean absolute error, root mean squared error, and R-squared, and strive to understand how to interpret the results from these metrics.
To get hands-on, we will implement linear regression by building a real-world use case where we predict employees’ salaries using various attributes. Here, we will learn in a hands-on fashion how to load and pre-process data, covering important ideas such as handling missing values, encoding categorical variables, and normalizing the data for modeling. Then, we will explore the process of building, compiling, and fitting a linear regression model...