Search⌘ K
AI Features
Home
Courses
Introduction to JAX and Deep Learning

Challenge II: Linear Regression

Understand how to build a linear regression model using JAX by implementing the regressor, defining a loss function, and optimizing parameters with gradient descent. This lesson helps consolidate skills in vectorization, auto-differentiation, and applying core linear algebra concepts in machine learning.

We'll cover the following...

We can consolidate our learning so far in a working example.

Since this course slightly favors machine or deep learning, we’ll practice with the ultimate 101 example: linear regression. In this challenge, you’ll build linear regression step-by-step.

Step 1: Regressor

Remember, linear regression fits the data point xx to a straight line:

y^=wx+b\hat{y} = wx+b

As a starter, this part simply requires us to implement the regressor, y^\hat{y}

Python 3.8
def Regressor(W,b):
  def y_(x):
    #Please update the line below with correct equation for y_
    return 1
  return y_

Step 2: Loss function

The loss function for a single sample is:

l(y′,y)=12(y′−y)2\mathcal l(y_{'},y) = \frac{1}{2}(y^{'}-y)^2 ...