We will now work on a project in which we will apply all the concepts we succinctly covered in the preceding pages. In this example, we will create one approximately linear distribution; afterwards, we will create a regression model that tries to fit a linear function that minimizes the error function (defined by least squares).
This model will allow us to predict an outcome for an input value, given one new sample.
For this example, we will be generating a synthetic dataset consisting of a linear function with added noise:
import TensorFlow as tf import numpy as np trX = np.linspace(-1, 1, 101) trY = 2 * trX + np.random.randn(*trX.shape) * 0.4 + 0.2 # create a y value which is approximately ...