521 views

Uploaded by Andres Tuells Jansson

j

- Artificial Intelligence
- Mini Project Report Sample
- 2_4_98 (1)
- Neuro Fuzzy thesis
- The Big Problem With Machine Learning Algorithms - Bloomberg.pdf
- Sap Concur Machine Learning White Paper 2018
- eBook Guide to Ai Qdn Final
- Image Processing with TensorFlow
- terpenos tipos 2
- Application of Neural Network for Arrhythmia Classification and Implementation of Effective Color Light Therapy
- International Conference on Artificial Intelligence and Soft Computing (AIS 2015)
- IJDIWC_Volume 6, Issue 1
- IJETTCS-2014-02-08-054
- Fifth International Conference on Artificial Intelligence
- 1412.5474v2
- HMPusingSVM_250
- Pottala Matias Thesis
- 1450-99031001001G
- Optimization of EDM by SA_ANN Method
- 29. M.E. CSE. (1)

You are on page 1of 10

A Step by Step

BackpropagationExample

Matt Mazur

Background

Home

About

Backpropagation is a common method for training a neural network. There is no

Archives

shortage of papers online that attempt to explain how backpropagation works,

Contact

but few that include an example with actual numbers. This post is my attempt to

Now

explain how it works with a concrete example that folks can compare their own

Projects

calculations to in order to ensure they understand backpropagation correctly.

If this kind of thing interests you, you should sign up for my newsletter where I

Enter your email address to follow

post about AI-related projects that Im working on.

this blog and receive notifications

of new posts by email.

Backpropagation in Python

Join 2,325 other followers

You can play around with a Python script that I wrote that implements the

Enter your email address

backpropagation algorithm in this Github repo.

Follow

Backpropagation Visualization

About

For an interactive visualization showing a neural network as it learns, check out

Hey there! I'm currently a data

my Neural Network visualization.

scientist Help Scout where I

wrangle data to gain insights into

our product and business. I also Additional Resources

built Lean Domain Search,

Preceden and many other If you find this tutorial useful and want to continue learning about neural

software products over the years.

networks and their applications, I highly recommend checking out Adrian

Rosebrocks excellent tutorial on Getting Started with Deep Learning and

Python.

Search

Overview

Follow me on Twitter

For this tutorial, were going to use a neural network with two inputs, two hidden

Tweets by @mhmazur neurons, two output neurons. Additionally, the hidden and output neurons will

include a bias.

Matt Mazur Retweeted

@lumatheodoro

clocks, which together form a

clock

https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/ 1/10

5/1/2017 A Step by Step Backpropagation Example Matt Mazur

23 Apr

Bill Gates

@BillGates

Indian Prime Minister

@narendramodi put a

spotlight on a subject that

most of us would rather not

even think about: b-

gat.es/2qbs2Kk

25 Apr

In order to have some numbers to work with, here are the initial weights, the

biases, and training inputs/outputs:

Matt Mazur Retweeted

Jason Cohen

@asmartbear

knowledge, high-

confidence theories

blog.asmartbear.com/low-

fact-trap.

25 Apr

Matt Mazur

@mhmazur

A Simple CROSS

JOIN Example

mattmazur.com/2017/04/23/a- The goal of backpropagation is to optimize the weights so that the neural

s

network can learn how to correctly map arbitrary inputs to outputs.

For the rest of this tutorial were going to work with a single training set: given

inputs 0.05 and 0.10, we want the neural network to output 0.01 and 0.99.

23 Apr To begin, lets see what the neural network currently predicts given the weights

and biases above and inputs of 0.05 and 0.10. To do this well feed those inputs

Matt Mazur Retweeted

forward though the network.

Adam Kucharski

@AdamJKucharski

We figure out the total net input to each hidden layer neuron, squash the total

Survivorship bias

xkcd.com/1827/ net input using an activation function (here we use the logistic function), then

repeat the process with the output layer neurons.

https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/ 2/10

5/1/2017 A Step by Step Backpropagation Example Matt Mazur

Total net input is also referred to as just net input by some sources.

21 Apr We then squash it using the logistic function to get the output of :

Tim Urban

@waitbutwhy

Carrying out the same process for we get:

It's finally here: the full story

on Neuralink. I knew the

future would be nuts but this

is a whole other level.

waitbutwhy.com/2017/04/neur We repeat this process for the output layer neurons, using the output from the

al

hidden layer neurons as inputs.

20 Apr

We can now calculate the error for each output neuron using the squared error

function and sum them to get the total error:

Some sources refer to the target as the ideal and the output as the actual.

on. The result is eventually multiplied by a learning rate anyway so it

doesnt matter that we introduce a constant here [1].

For example, the target output for is 0.01 but the neural network output

0.75136507, therefore its error is:

https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/ 3/10

5/1/2017 A Step by Step Backpropagation Example Matt Mazur

Repeating this process for (remembering that the target is 0.99) we get:

The total error for the neural network is the sum of these errors:

Our goal with backpropagation is to update each of the weights in the network

so that they cause the actual output to be closer the target output, thereby

minimizing the error for each output neuron and the network as a whole.

Output Layer

Consider . We want to know how much a change in affects the total error,

aka .

can also say the gradient with respect to .

First, how much does the total error change with respect to the output?

https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/ 4/10

5/1/2017 A Step by Step Backpropagation Example Matt Mazur

is sometimes expressed as

When we take the partial derivative of the total error with respect to ,

the quantity becomes zero because does not

affect it which means were taking the derivative of a constant which is

zero.

Next, how much does the output of change with respect to its total net input?

The partial derivative of the logistic function is the output multiplied by 1 minus

the output:

Finally, how much does the total net input of change with respect to ?

Youll often see this calculation combined in the form of the delta rule:

aka (the Greek letter delta) aka the node delta. We can use this to

rewrite the calculation above:

Therefore:

Some sources extract the negative sign from so it would be written as:

https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/ 5/10

5/1/2017 A Step by Step Backpropagation Example Matt Mazur

To decrease the error, we then subtract this value from the current weight

(optionally multiplied by some learning rate, eta, which well set to 0.5):

Some sources use (alpha) to represent the learning rate, others use

(eta), and others even use (epsilon).

We perform the actual updates in the neural network after we have the new

weights leading into the hidden layer neurons (ie, we use the original weights,

not the updated weights, when we continue the backpropagation algorithm

below).

Hidden Layer

Next, well continue the backwards pass by calculating new values for , ,

, and .

Visually:

https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/ 6/10

5/1/2017 A Step by Step Backpropagation Example Matt Mazur

Were going to use a similar process as we did for the output layer, but slightly

different to account for the fact that the output of each hidden layer neuron

contributes to the output (and therefore error) of multiple output neurons. We

know that affects both and therefore the needs to take

into consideration its effect on the both output neurons:

Starting with :

And is equal to :

Therefore:

Now that we have , we need to figure out and then for each

weight:

We calculate the partial derivative of the total net input to with respect to

the same as we did for the output neuron:

https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/ 7/10

5/1/2017 A Step by Step Backpropagation Example Matt Mazur

Finally, weve updated all of our weights! When we fed forward the 0.05 and 0.1

inputs originally, the error on the network was 0.298371109. After this first round

of backpropagation, the total error is now down to 0.291027924. It might not

seem like much, but after repeating this process 10,000 times, for example, the

error plummets to 0.000035085. At this point, when we feed forward 0.05 and

0.1, the two outputs neurons generate 0.015912196 (vs 0.01 target) and

0.984065734 (vs 0.99 target).

If youve made it this far and found any errors in any of the above or can think of

any ways to make it clearer for future readers, dont hesitate to drop me a note.

Thanks!

Share this:

Like

49 bloggers like this.

Related

Mind Neural Network-based In "Emergent Mind"

In "Emergent Mind" Poker Bot

In "Poker Bot"

Posted on March 17, 2015 by Mazur. This entry was posted in Machine Learning and tagged ai,

backpropagation, machine learning, neural networks. Bookmark the permalink.

https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/ 8/10

5/1/2017 A Step by Step Backpropagation Example Matt Mazur

an Open Source A/B Test on Github

Significance Calculator

Older Comments

yoba

April 16, 2017 at 5:05 am

Reply

Himanshu

April 17, 2017 at 5:25 am

Reply

MaviccPRP

April 18, 2017 at 2:39 am

Really good tutorial Matt. I finally had something like a aha moment ;-)

With the inspiration of this tutorial I translated this real number example into matrix

multiplication operations.

Reply

jerpint

April 18, 2017 at 1:13 pm

Hello, thanks for your explanation. Can you please clarify why the biases b1 and b2 are

the same for their entire

respective layers? Shouldnt we have a bias vector b of the same length as the number of

neurons per layer?

Reply

Paul Martin

April 18, 2017 at 2:39 pm

Like to print things out and read over. Seems like the print out starts omitting detail once

it hits the hidden layers. Odd. All in all this is quite helpful to understand the back

propagation.

Reply

https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/ 9/10

5/1/2017 A Step by Step Backpropagation Example Matt Mazur

Ab

April 24, 2017 at 5:35 pm

Reply

KG

April 25, 2017 at 7:41 pm

Reply

mahdi

April 25, 2017 at 7:52 pm

mahadi army

Reply

Older Comments

Leave a Reply

Blog at WordPress.com.

https://mattmazur.com/2015/03/17/a-step-by-step-backpropagation-example/ 10/10

- Artificial IntelligenceUploaded bySmoore Core
- Mini Project Report SampleUploaded bySakshi Issar
- 2_4_98 (1)Uploaded bydeemi75
- Neuro Fuzzy thesisUploaded byJamila Saeed
- The Big Problem With Machine Learning Algorithms - Bloomberg.pdfUploaded byJoe Smith
- Sap Concur Machine Learning White Paper 2018Uploaded byArtha Shastri
- eBook Guide to Ai Qdn FinalUploaded byoeortizm
- Image Processing with TensorFlowUploaded byMarc Reyes
- terpenos tipos 2Uploaded byOctavio Carbajal
- Application of Neural Network for Arrhythmia Classification and Implementation of Effective Color Light TherapyUploaded byJournalofICT
- International Conference on Artificial Intelligence and Soft Computing (AIS 2015)Uploaded byCS & IT
- IJDIWC_Volume 6, Issue 1Uploaded byIJDIWC
- IJETTCS-2014-02-08-054Uploaded byAnonymous vQrJlEN
- Fifth International Conference on Artificial IntelligenceUploaded byCS & IT
- 1412.5474v2Uploaded byMega Ariyanfina
- HMPusingSVM_250Uploaded byUsman Tariq
- Pottala Matias ThesisUploaded byIsa Adela
- 1450-99031001001GUploaded byAhmet Rizaner
- Optimization of EDM by SA_ANN MethodUploaded byaghosh704
- 29. M.E. CSE. (1)Uploaded byCibil.Rittu1719 MBA
- Learning MeaningUploaded bybearshen
- 1-s2.0-S1574013709000173-mainUploaded byYessica Rosas
- A Survey of Offline Handwritten Signature RecognitionUploaded bydipan banerjee
- 2007 IEEE Tr Power Deliv Load BalanceUploaded byRajashekar
- Zan Huanga, Hsinchun Chena, Chia-Jung Hsua, Wun-Hwa Chenb, Soushan Wu - Credit Rating Analysis With Support Vector Machines and Neural NetworksUploaded byhenrique_oliv
- Additional Notes on BackpropagationUploaded byballsarini a
- 10.1.1.116.370Uploaded bySuhail Khokhar
- grnn advancedUploaded byDiyar M Khalil
- SSCIvol01no02paper02Uploaded byGeorge Chiu
- Nuclear PP Diagnosis FaultUploaded bysuder

- Geometric Algebra Primer - Jaap Suter - 2003Uploaded byJaapSuter
- Learning Deep Learning With KerasUploaded byAndres Tuells Jansson
- Bombjoke Comments on I'm a Piece of Shit. No More Games, No More Lies, No More Excuses. I Need DisciplineUploaded byAndres Tuells Jansson
- The Power Ofdl to Express Natural FunctionsUploaded byAndres Tuells Jansson
- Deep Learning (2016.09.23-00.17.14Z).epubUploaded byAndres Tuells Jansson
- Hello, TensorFlow! - O'Reilly MediaUploaded byAndres Tuells Jansson
- 496fed6eca4452e569fbac8d41a12cedd703Uploaded byAndres Tuells Jansson
- Wald.-.Gravitation,Thermodynamics.and.Quantum.Theory.(1999)Uploaded byAlex Albuquerque
- 9904050Uploaded byAndres Tuells Jansson
- Thank You R_theXeffect! _ TheXeffectUploaded byAndres Tuells Jansson
- awda-preview-trollkiller.pdfUploaded byAndres Tuells Jansson
- junipers-guide-to-fascists.docUploaded byAndres Tuells Jansson
- mixture of gaussiansUploaded byAshwini Kumar Pal
- awda-preview-rights.pdfUploaded byAndres Tuells Jansson
- PerceptronUploaded byapi-3814100
- deepwarp_eccv2016Uploaded byAndres Tuells Jansson
- ESANNUploaded byAndres Tuells Jansson
- Space InvadersUploaded byAndres Tuells Jansson
- 1006.2483v2.pdfUploaded byAndres Tuells Jansson
- 1704.01568Uploaded byPeter Pan
- Zeiler Ec Cv 2014Uploaded byVaibhav Jain
- 1704.05539.pdfUploaded byAndres Tuells Jansson
- springUploaded bypetekrem59
- Some Deep Learning ResourcesUploaded byaliasvicko
- Neural Networks and Deep LearningUploaded byAndres Tuells Jansson
- An Introduction to Geometric Algebra over R^2 _ BitWorkingUploaded byAndres Tuells Jansson
- Deep Learning Tutorial Release 0.1Uploaded bylerhlerh
- Why Does Deep and Cheap Learning Work Soo WellUploaded byAndres Tuells Jansson
- Why Does Deep and Cheap Learning Work Soo WellUploaded byAndres Tuells Jansson

- Fully complex elmUploaded byFreddy Osvaldo Sánchez Castro
- Tea Insect Pests Classification Based on Artificial NeuralUploaded byMax Reagan
- PPT12.pptUploaded byPosess Mogapi
- Poisonous MushroomsUploaded bySamuel Peoples
- ANFIS.pptUploaded byShimaa Barakat
- 4 - Face RecognitionUploaded byNasrin Dorreh
- Data Science - List of PackagesUploaded byDeepak Gupta
- neuroscience and computersUploaded byapi-285917085
- Image Classification With DIGITS HryuUploaded byBreno Brito Miranda
- AI History 2Uploaded byAnsh Rana
- 181704-2181710-SCCUploaded byBhautik Daxini
- An Incremental on-Line Chinese Handwriting Recognition SystemUploaded bysm-malik
- deeplearningbfci-170626220653Uploaded byasf
- R Machine Learning.pdfUploaded byAnonymous NoermyAEpd
- FuzzyUploaded bytidjani86
- 1_DBNUploaded byanoopingle9
- Fall 2016 Chapter 1 Lecture 3Uploaded byTan Quoc Huynh
- The Effect of Data Quality in Machine Learning Through Chess Engine PerformanceUploaded byAustin Lehman
- Image Binarization Using Otsu Method 20090420Uploaded byPoly Bora
- MATLAB DEEP LEARNING - Phil Kim.pdfUploaded byDaniel Alexei López Marín
- MachineLearningNotes.docxUploaded byIshan Sane
- Fifth Generation - Present and Beyond:Artificial Intelligence Advance VersionUploaded byYasir Ahmed
- Artificial Neural Networks - Utec AiUploaded byBregy Esteban Malpartida Ramos
- 10.1.1.124.7488Uploaded byJovid Rakhmonov
- Brain GateUploaded byRajesh Lenka
- Cv Dl Resource GuideUploaded byGrant imahara
- 17_chapter 6.pdfUploaded byNileshNemade
- sol11Uploaded byHoda Hosny
- neural networksUploaded byAswin Kumar
- lec-1 CS188Uploaded byRoven Chan