Example 1Lesson 23Free preview

Ex1 Intro

This lesson is part of A.I. · All levels

Summary

The first example TensorFlow.js predicts the value of y from the value of x having a near-linear relationship. We set up the data in tensors x and y, we make a simple model, then we train and use it to guess. This example is an introductory step before we get into the data and the more detailed models.

Key points

The purpose of the example: predict y from one feature of x (regress of one variable).
Data is two one-dimensional tensors: x as input and y as output.
The x- and y-relationships are almost linear, so they're perfect for a simple model.
The workflow: prepare the data, model, practice, then predict.

Full lesson

Code examples and quizzes

Full lessons, code examples, and quizzes are available to subscribers. 5 questions.