Search icon CANCEL
Subscription
0
Cart icon
Your Cart (0 item)
Close icon
You have no products in your basket yet
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Deep Learning from the Basics

You're reading from   Deep Learning from the Basics Python and Deep Learning: Theory and Implementation

Arrow left icon
Product type Paperback
Published in Mar 2021
Publisher Packt
ISBN-13 9781800206137
Length 316 pages
Edition 1st Edition
Languages
Arrow right icon
Authors (2):
Arrow left icon
Shigeo Yushita Shigeo Yushita
Author Profile Icon Shigeo Yushita
Shigeo Yushita
Koki Saitoh Koki Saitoh
Author Profile Icon Koki Saitoh
Koki Saitoh
Arrow right icon
View More author details
Toc

Table of Contents (11) Chapters Close

Preface Introduction 1. Introduction to Python FREE CHAPTER 2. Perceptrons 3. Neural Networks 4. Neural Network Training 5. Backpropagation 6. Training Techniques 7. Convolutional Neural Networks 8. Deep Learning Appendix A

Backward Propagation

The previous section described how backward propagation in a computational graph is based on the chain rule. We will now cover how backward propagation works by taking operations, such as "+" and "x", as examples.

Backward Propagation in an Addition Node

First, let's consider backward propagation in an additional node. Here, we will look at backward propagation for the equation z = x + y. We can obtain the derivatives of z = x + y (analytically) as follows:

13

(5.5)

As equation (5.5) shows, both 15 and 16 are 1. Therefore, we can represent them in a computational graph, as shown in the following diagram. In backward propagation, the derivative from the upper stream—17, in this example—is multiplied by 1 and passed downstream. In short, backward propagation in an addition node multiplies 1, so it only passes the input value to the...

lock icon The rest of the chapter is locked
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at $19.99/month. Cancel anytime
Banner background image