In this course, you will learn the fundamental principles of deep learning by building your very own neural network components completely from scratch. You'll learn about the history of neural networks and then start building your own library with linear layers, weight initializers, dropout, various regularizers, and batch norm. From there, you'll also learn the math and theory underpinning each of these components. We'll integrate material from statistics, numerical analysis, and Bayesian statistics to give you the most well rounded perspective of deep learning available in any course. View the entire course syllabus below, along with preview lessons. Be sure to click the drop down arrow to see the syllabus in its entirety.

Course Curriculum

  Course Introduction
Available in days
days after you enroll
  Why Do We Care So Much About Neural Networks?
Available in days
days after you enroll
  Neural Network Module
Available in days
days after you enroll
  Resources, References, and Course Credits
Available in days
days after you enroll

Select a pricing plan and sign up

$99

Unlimited Access

Get unlimited access to this course

Get unlimited access to this course for a fixed price.