Two-dimensional curve fitting

In this section, we are going to implement an application so that we can fit the given two-dimensional curve using the polynomial model. Previously, we saw that the polynomial model can emulate any function if we can calculate the sum of its terms infinitely. Let's see what prediction looks like with the two-degree polynomial model.

Preparing the dataset

First, we are going to prepare the dataset. The dataset is two numerical sequences representing x and y values in a two-dimensional space. The target value to be predicted by the model is a sine curve in each point. To make the situation as close to the real world as possible, we have added Gaussian random noise to the target value.

tf.randomNormal...