Modifying the loss function

In the previous exercise, you defined a tensorflow loss function and then evaluated it once for a set of actual and predicted values. In this exercise, you will compute the loss within another function called loss_function(), which first generates predicted values from the data and variables. The purpose of this is to construct a function of the trainable model variables that returns the loss. You can then repeatedly evaluate this function for different variable values until you find the minimum. In practice, you will pass this function to an optimizer in tensorflow. Note that features and targets have been defined and are available. Additionally, Variable, float32, and keras are available.

Define a variable, scalar, with an initial value of 1.0 and a type of float32.
Define a function called loss_function(), which takes scalar, features, and targets as arguments in that order.
Use a mean absolute error loss function.

Exercise

Modifying the loss function

Instructions