SlideShare a Scribd company logo
1 of 16
@tdevinda
Artificial Neural Networks
An Introduction
@tdevinda
@tdevinda
Anatomy of the biological neuron
@tdevinda
Biological neuron: Synapse
@tdevinda
Anatomy of an artificial neuron
Sometimes this is referred to as a
“Perceptron” as well.
A perceptron is a machine which
perceives the input and produces
an output
@tdevinda
Activation, Weight
and Bias
Activation denotes the amount of
activity of the neuron. (A measure of
how ‘charged’ the neuron is)
This activation output is passed over
to the next neuron as inputs for that
neuron
Activations from inputs is weighted.
Each input has its own weight (Wi)
Each neuron has an internal “Bias”
Weighted sum and the bias makes up
the activation of a neuron
W0
W1
W2
b
@tdevinda
Calculation of the activation
● Activation is the weighted sum of all inputs
Weighted Sum =
● In order to make the output more generalized, we use a function on this sum.
This function is called the activation function.
● An activation function for example would generalize the output to a value
between 0 and 1
W0
W1
W2
b
x0
x1
x2
@tdevinda
Calculation of the activation
● There are many activation functions available
○ Sigmoid
○ ReLU
○ Tanh
● Now the output becomes
W0
W1
W2
b
x0
x1
x2
@tdevinda
Calculation of the activation - The use of a “bias”
● When the activation function is used without any alterations, we cannot
control the output with input parameters
● The addition of a “BIAS” helps to move the function left-right.
● Bias tells when the neuron gets to be active
● Now the output is
@tdevinda
A complete ANN
● The combined product of these neurons
becomes an ‘Artificial Neural Network’
● Neurons getting triggered together work as
a ‘layer’
● There is an ‘INPUT’ layer and an ‘OUTPUT’
layer.
● There can be ‘HIDDEN’ layers in between.
● At the output, many neurons would be
‘active’ or ‘inactive’
● If this is a network which does a
classification, we’d want the right neurons
to be ‘active’
@tdevinda
Definition of cost
● When the neural network produces the output, it would naturally vary from the
desired output.
● This difference is the ‘cost’ of the result
● We obtain the cost of a network, by running all training samples through and
averaging the result.
● What we need to do is to minimize this ‘cost’ so that the right results are
produced every time we input data
@tdevinda
Reduction of the cost
● Getting a zero cost is the ultimate goal.
● But we’d never get to zero
● We will alter the parameters to get to a minimum possible value
○ Alterations to weights
○ Alterations to biases
● We try to find a minimum point in a multi-dimensional plane
● Good old partial differentials come into play
=
@tdevinda
Gradient descent
● What we actually do is to reach a point in the n-dimensional plane, where a
minima exists.
● Gets simple when you look at 1 or 2 dimensional inputs
@tdevinda
Learning - Back propagation
● When we have the cost, we devise the
methodology to change the weights and
biases of each neuron depending on the
gradients
● This methodology is called back propagation
● Our calculation of a back propagation function
tells us how much to change the weights and
biases
● After each change, we run the samples again,
and repeat, until we get to a minimum cost
@tdevinda
Many Types of ANNs
● Many types of ANNs exist
● What we tried is a multi-layered perceptron
● Different types are used for different
applications
● Convolutional Neural Networks (CNNs):
○ Used for image classifications
○ Uses filters to detect certain features of images
● Recurrent Neural Network (RNNs):
○ Used for speech recognition
○ Contains feedback points from next layers or current
layer
Many more...
@tdevinda
Artificial Neural Networks
An Introduction

More Related Content

Similar to Artificial Neural Networks - An Introduction.pptx

Artificial neural networks
Artificial neural networksArtificial neural networks
Artificial neural networksarjitkantgupta
 
Neural Networks Lec3.pptx
Neural Networks Lec3.pptxNeural Networks Lec3.pptx
Neural Networks Lec3.pptxmoah92926
 
Artificial Neural Network_VCW (1).pptx
Artificial Neural Network_VCW (1).pptxArtificial Neural Network_VCW (1).pptx
Artificial Neural Network_VCW (1).pptxpratik610182
 
Multilayer Perceptron Neural Network MLP
Multilayer Perceptron Neural Network MLPMultilayer Perceptron Neural Network MLP
Multilayer Perceptron Neural Network MLPAbdullah al Mamun
 
Introduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkKnoldus Inc.
 
Deep neural networks & computational graphs
Deep neural networks & computational graphsDeep neural networks & computational graphs
Deep neural networks & computational graphsRevanth Kumar
 
Machine Learning With Neural Networks
Machine Learning  With Neural NetworksMachine Learning  With Neural Networks
Machine Learning With Neural NetworksKnoldus Inc.
 
Recurrent Neural Networks
Recurrent Neural NetworksRecurrent Neural Networks
Recurrent Neural NetworksCloudxLab
 
08 neural networks
08 neural networks08 neural networks
08 neural networksankit_ppt
 
Introduction to Perceptron and Neural Network.pptx
Introduction to Perceptron and Neural Network.pptxIntroduction to Perceptron and Neural Network.pptx
Introduction to Perceptron and Neural Network.pptxPoonam60376
 
Introduction to Deep learning and H2O for beginner's
Introduction to Deep learning and H2O for beginner'sIntroduction to Deep learning and H2O for beginner's
Introduction to Deep learning and H2O for beginner'sVidyasagar Bhargava
 
Supervised Learning.pptx
Supervised Learning.pptxSupervised Learning.pptx
Supervised Learning.pptxShishir Ahmed
 
20200428135045cfbc718e2c.pdf
20200428135045cfbc718e2c.pdf20200428135045cfbc718e2c.pdf
20200428135045cfbc718e2c.pdfTitleTube
 
Activation_function.pptx
Activation_function.pptxActivation_function.pptx
Activation_function.pptxMohamed Essam
 
Dr. Syed Muhammad Ali Tirmizi - Special topics in finance lec 13
Dr. Syed Muhammad Ali Tirmizi - Special topics in finance   lec 13Dr. Syed Muhammad Ali Tirmizi - Special topics in finance   lec 13
Dr. Syed Muhammad Ali Tirmizi - Special topics in finance lec 13Dr. Muhammad Ali Tirmizi., Ph.D.
 

Similar to Artificial Neural Networks - An Introduction.pptx (20)

Artificial neural networks
Artificial neural networksArtificial neural networks
Artificial neural networks
 
Neural Networks Lec3.pptx
Neural Networks Lec3.pptxNeural Networks Lec3.pptx
Neural Networks Lec3.pptx
 
Artificial Neural Network_VCW (1).pptx
Artificial Neural Network_VCW (1).pptxArtificial Neural Network_VCW (1).pptx
Artificial Neural Network_VCW (1).pptx
 
UNIT 5-ANN.ppt
UNIT 5-ANN.pptUNIT 5-ANN.ppt
UNIT 5-ANN.ppt
 
Multilayer Perceptron Neural Network MLP
Multilayer Perceptron Neural Network MLPMultilayer Perceptron Neural Network MLP
Multilayer Perceptron Neural Network MLP
 
Introduction to Recurrent Neural Network
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural Network
 
Deep neural networks & computational graphs
Deep neural networks & computational graphsDeep neural networks & computational graphs
Deep neural networks & computational graphs
 
Machine Learning With Neural Networks
Machine Learning  With Neural NetworksMachine Learning  With Neural Networks
Machine Learning With Neural Networks
 
Recurrent Neural Networks
Recurrent Neural NetworksRecurrent Neural Networks
Recurrent Neural Networks
 
Unit 6: Application of AI
Unit 6: Application of AIUnit 6: Application of AI
Unit 6: Application of AI
 
08 neural networks
08 neural networks08 neural networks
08 neural networks
 
NNAF_DRK.pdf
NNAF_DRK.pdfNNAF_DRK.pdf
NNAF_DRK.pdf
 
ANN.pptx
ANN.pptxANN.pptx
ANN.pptx
 
Introduction to Perceptron and Neural Network.pptx
Introduction to Perceptron and Neural Network.pptxIntroduction to Perceptron and Neural Network.pptx
Introduction to Perceptron and Neural Network.pptx
 
Neural Network
Neural NetworkNeural Network
Neural Network
 
Introduction to Deep learning and H2O for beginner's
Introduction to Deep learning and H2O for beginner'sIntroduction to Deep learning and H2O for beginner's
Introduction to Deep learning and H2O for beginner's
 
Supervised Learning.pptx
Supervised Learning.pptxSupervised Learning.pptx
Supervised Learning.pptx
 
20200428135045cfbc718e2c.pdf
20200428135045cfbc718e2c.pdf20200428135045cfbc718e2c.pdf
20200428135045cfbc718e2c.pdf
 
Activation_function.pptx
Activation_function.pptxActivation_function.pptx
Activation_function.pptx
 
Dr. Syed Muhammad Ali Tirmizi - Special topics in finance lec 13
Dr. Syed Muhammad Ali Tirmizi - Special topics in finance   lec 13Dr. Syed Muhammad Ali Tirmizi - Special topics in finance   lec 13
Dr. Syed Muhammad Ali Tirmizi - Special topics in finance lec 13
 

More from Tharaka Devinda

Firebase Basics - Dialog Demo for Group Tech Staff
Firebase Basics - Dialog Demo for Group Tech StaffFirebase Basics - Dialog Demo for Group Tech Staff
Firebase Basics - Dialog Demo for Group Tech StaffTharaka Devinda
 
Timetrek internals - Firebase with Google Cloud for a web based game
Timetrek internals - Firebase with Google Cloud for a web based gameTimetrek internals - Firebase with Google Cloud for a web based game
Timetrek internals - Firebase with Google Cloud for a web based gameTharaka Devinda
 
Introduction to Android - Session 3
Introduction to Android - Session 3Introduction to Android - Session 3
Introduction to Android - Session 3Tharaka Devinda
 

More from Tharaka Devinda (6)

Introduction to Docker
Introduction to DockerIntroduction to Docker
Introduction to Docker
 
Firebase Basics - Dialog Demo for Group Tech Staff
Firebase Basics - Dialog Demo for Group Tech StaffFirebase Basics - Dialog Demo for Group Tech Staff
Firebase Basics - Dialog Demo for Group Tech Staff
 
Timetrek internals - Firebase with Google Cloud for a web based game
Timetrek internals - Firebase with Google Cloud for a web based gameTimetrek internals - Firebase with Google Cloud for a web based game
Timetrek internals - Firebase with Google Cloud for a web based game
 
Introduction to Android - Session 3
Introduction to Android - Session 3Introduction to Android - Session 3
Introduction to Android - Session 3
 
Introduction to Android
Introduction to AndroidIntroduction to Android
Introduction to Android
 
ASN.1 Basics
ASN.1 BasicsASN.1 Basics
ASN.1 Basics
 

Recently uploaded

Human Expert Website Manual WCAG 2.0 2.1 2.2 Audit - Digital Accessibility Au...
Human Expert Website Manual WCAG 2.0 2.1 2.2 Audit - Digital Accessibility Au...Human Expert Website Manual WCAG 2.0 2.1 2.2 Audit - Digital Accessibility Au...
Human Expert Website Manual WCAG 2.0 2.1 2.2 Audit - Digital Accessibility Au...Skynet Technologies
 
Design Guidelines for Passkeys 2024.pptx
Design Guidelines for Passkeys 2024.pptxDesign Guidelines for Passkeys 2024.pptx
Design Guidelines for Passkeys 2024.pptxFIDO Alliance
 
Tales from a Passkey Provider Progress from Awareness to Implementation.pptx
Tales from a Passkey Provider  Progress from Awareness to Implementation.pptxTales from a Passkey Provider  Progress from Awareness to Implementation.pptx
Tales from a Passkey Provider Progress from Awareness to Implementation.pptxFIDO Alliance
 
“Iamnobody89757” Understanding the Mysterious of Digital Identity.pdf
“Iamnobody89757” Understanding the Mysterious of Digital Identity.pdf“Iamnobody89757” Understanding the Mysterious of Digital Identity.pdf
“Iamnobody89757” Understanding the Mysterious of Digital Identity.pdfMuhammad Subhan
 
2024 May Patch Tuesday
2024 May Patch Tuesday2024 May Patch Tuesday
2024 May Patch TuesdayIvanti
 
Oauth 2.0 Introduction and Flows with MuleSoft
Oauth 2.0 Introduction and Flows with MuleSoftOauth 2.0 Introduction and Flows with MuleSoft
Oauth 2.0 Introduction and Flows with MuleSoftshyamraj55
 
Six Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal OntologySix Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal Ontologyjohnbeverley2021
 
JohnPollard-hybrid-app-RailsConf2024.pptx
JohnPollard-hybrid-app-RailsConf2024.pptxJohnPollard-hybrid-app-RailsConf2024.pptx
JohnPollard-hybrid-app-RailsConf2024.pptxJohnPollard37
 
الأمن السيبراني - ما لا يسع للمستخدم جهله
الأمن السيبراني - ما لا يسع للمستخدم جهلهالأمن السيبراني - ما لا يسع للمستخدم جهله
الأمن السيبراني - ما لا يسع للمستخدم جهلهMohamed Sweelam
 
How to Check GPS Location with a Live Tracker in Pakistan
How to Check GPS Location with a Live Tracker in PakistanHow to Check GPS Location with a Live Tracker in Pakistan
How to Check GPS Location with a Live Tracker in Pakistandanishmna97
 
CORS (Kitworks Team Study 양다윗 발표자료 240510)
CORS (Kitworks Team Study 양다윗 발표자료 240510)CORS (Kitworks Team Study 양다윗 발표자료 240510)
CORS (Kitworks Team Study 양다윗 발표자료 240510)Wonjun Hwang
 
ERP Contender Series: Acumatica vs. Sage Intacct
ERP Contender Series: Acumatica vs. Sage IntacctERP Contender Series: Acumatica vs. Sage Intacct
ERP Contender Series: Acumatica vs. Sage IntacctBrainSell Technologies
 
Portal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russePortal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russe中 央社
 
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)Samir Dash
 
How to Check CNIC Information Online with Pakdata cf
How to Check CNIC Information Online with Pakdata cfHow to Check CNIC Information Online with Pakdata cf
How to Check CNIC Information Online with Pakdata cfdanishmna97
 
Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...
Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...
Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...ScyllaDB
 
Introduction to use of FHIR Documents in ABDM
Introduction to use of FHIR Documents in ABDMIntroduction to use of FHIR Documents in ABDM
Introduction to use of FHIR Documents in ABDMKumar Satyam
 
Design and Development of a Provenance Capture Platform for Data Science
Design and Development of a Provenance Capture Platform for Data ScienceDesign and Development of a Provenance Capture Platform for Data Science
Design and Development of a Provenance Capture Platform for Data SciencePaolo Missier
 
State of the Smart Building Startup Landscape 2024!
State of the Smart Building Startup Landscape 2024!State of the Smart Building Startup Landscape 2024!
State of the Smart Building Startup Landscape 2024!Memoori
 
Working together SRE & Platform Engineering
Working together SRE & Platform EngineeringWorking together SRE & Platform Engineering
Working together SRE & Platform EngineeringMarcus Vechiato
 

Recently uploaded (20)

Human Expert Website Manual WCAG 2.0 2.1 2.2 Audit - Digital Accessibility Au...
Human Expert Website Manual WCAG 2.0 2.1 2.2 Audit - Digital Accessibility Au...Human Expert Website Manual WCAG 2.0 2.1 2.2 Audit - Digital Accessibility Au...
Human Expert Website Manual WCAG 2.0 2.1 2.2 Audit - Digital Accessibility Au...
 
Design Guidelines for Passkeys 2024.pptx
Design Guidelines for Passkeys 2024.pptxDesign Guidelines for Passkeys 2024.pptx
Design Guidelines for Passkeys 2024.pptx
 
Tales from a Passkey Provider Progress from Awareness to Implementation.pptx
Tales from a Passkey Provider  Progress from Awareness to Implementation.pptxTales from a Passkey Provider  Progress from Awareness to Implementation.pptx
Tales from a Passkey Provider Progress from Awareness to Implementation.pptx
 
“Iamnobody89757” Understanding the Mysterious of Digital Identity.pdf
“Iamnobody89757” Understanding the Mysterious of Digital Identity.pdf“Iamnobody89757” Understanding the Mysterious of Digital Identity.pdf
“Iamnobody89757” Understanding the Mysterious of Digital Identity.pdf
 
2024 May Patch Tuesday
2024 May Patch Tuesday2024 May Patch Tuesday
2024 May Patch Tuesday
 
Oauth 2.0 Introduction and Flows with MuleSoft
Oauth 2.0 Introduction and Flows with MuleSoftOauth 2.0 Introduction and Flows with MuleSoft
Oauth 2.0 Introduction and Flows with MuleSoft
 
Six Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal OntologySix Myths about Ontologies: The Basics of Formal Ontology
Six Myths about Ontologies: The Basics of Formal Ontology
 
JohnPollard-hybrid-app-RailsConf2024.pptx
JohnPollard-hybrid-app-RailsConf2024.pptxJohnPollard-hybrid-app-RailsConf2024.pptx
JohnPollard-hybrid-app-RailsConf2024.pptx
 
الأمن السيبراني - ما لا يسع للمستخدم جهله
الأمن السيبراني - ما لا يسع للمستخدم جهلهالأمن السيبراني - ما لا يسع للمستخدم جهله
الأمن السيبراني - ما لا يسع للمستخدم جهله
 
How to Check GPS Location with a Live Tracker in Pakistan
How to Check GPS Location with a Live Tracker in PakistanHow to Check GPS Location with a Live Tracker in Pakistan
How to Check GPS Location with a Live Tracker in Pakistan
 
CORS (Kitworks Team Study 양다윗 발표자료 240510)
CORS (Kitworks Team Study 양다윗 발표자료 240510)CORS (Kitworks Team Study 양다윗 발표자료 240510)
CORS (Kitworks Team Study 양다윗 발표자료 240510)
 
ERP Contender Series: Acumatica vs. Sage Intacct
ERP Contender Series: Acumatica vs. Sage IntacctERP Contender Series: Acumatica vs. Sage Intacct
ERP Contender Series: Acumatica vs. Sage Intacct
 
Portal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russePortal Kombat : extension du réseau de propagande russe
Portal Kombat : extension du réseau de propagande russe
 
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)
AI+A11Y 11MAY2024 HYDERBAD GAAD 2024 - HelloA11Y (11 May 2024)
 
How to Check CNIC Information Online with Pakdata cf
How to Check CNIC Information Online with Pakdata cfHow to Check CNIC Information Online with Pakdata cf
How to Check CNIC Information Online with Pakdata cf
 
Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...
Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...
Event-Driven Architecture Masterclass: Integrating Distributed Data Stores Ac...
 
Introduction to use of FHIR Documents in ABDM
Introduction to use of FHIR Documents in ABDMIntroduction to use of FHIR Documents in ABDM
Introduction to use of FHIR Documents in ABDM
 
Design and Development of a Provenance Capture Platform for Data Science
Design and Development of a Provenance Capture Platform for Data ScienceDesign and Development of a Provenance Capture Platform for Data Science
Design and Development of a Provenance Capture Platform for Data Science
 
State of the Smart Building Startup Landscape 2024!
State of the Smart Building Startup Landscape 2024!State of the Smart Building Startup Landscape 2024!
State of the Smart Building Startup Landscape 2024!
 
Working together SRE & Platform Engineering
Working together SRE & Platform EngineeringWorking together SRE & Platform Engineering
Working together SRE & Platform Engineering
 

Artificial Neural Networks - An Introduction.pptx

  • 3. @tdevinda Anatomy of the biological neuron
  • 5. @tdevinda Anatomy of an artificial neuron Sometimes this is referred to as a “Perceptron” as well. A perceptron is a machine which perceives the input and produces an output
  • 6. @tdevinda Activation, Weight and Bias Activation denotes the amount of activity of the neuron. (A measure of how ‘charged’ the neuron is) This activation output is passed over to the next neuron as inputs for that neuron Activations from inputs is weighted. Each input has its own weight (Wi) Each neuron has an internal “Bias” Weighted sum and the bias makes up the activation of a neuron W0 W1 W2 b
  • 7. @tdevinda Calculation of the activation ● Activation is the weighted sum of all inputs Weighted Sum = ● In order to make the output more generalized, we use a function on this sum. This function is called the activation function. ● An activation function for example would generalize the output to a value between 0 and 1 W0 W1 W2 b x0 x1 x2
  • 8. @tdevinda Calculation of the activation ● There are many activation functions available ○ Sigmoid ○ ReLU ○ Tanh ● Now the output becomes W0 W1 W2 b x0 x1 x2
  • 9. @tdevinda Calculation of the activation - The use of a “bias” ● When the activation function is used without any alterations, we cannot control the output with input parameters ● The addition of a “BIAS” helps to move the function left-right. ● Bias tells when the neuron gets to be active ● Now the output is
  • 10. @tdevinda A complete ANN ● The combined product of these neurons becomes an ‘Artificial Neural Network’ ● Neurons getting triggered together work as a ‘layer’ ● There is an ‘INPUT’ layer and an ‘OUTPUT’ layer. ● There can be ‘HIDDEN’ layers in between. ● At the output, many neurons would be ‘active’ or ‘inactive’ ● If this is a network which does a classification, we’d want the right neurons to be ‘active’
  • 11. @tdevinda Definition of cost ● When the neural network produces the output, it would naturally vary from the desired output. ● This difference is the ‘cost’ of the result ● We obtain the cost of a network, by running all training samples through and averaging the result. ● What we need to do is to minimize this ‘cost’ so that the right results are produced every time we input data
  • 12. @tdevinda Reduction of the cost ● Getting a zero cost is the ultimate goal. ● But we’d never get to zero ● We will alter the parameters to get to a minimum possible value ○ Alterations to weights ○ Alterations to biases ● We try to find a minimum point in a multi-dimensional plane ● Good old partial differentials come into play =
  • 13. @tdevinda Gradient descent ● What we actually do is to reach a point in the n-dimensional plane, where a minima exists. ● Gets simple when you look at 1 or 2 dimensional inputs
  • 14. @tdevinda Learning - Back propagation ● When we have the cost, we devise the methodology to change the weights and biases of each neuron depending on the gradients ● This methodology is called back propagation ● Our calculation of a back propagation function tells us how much to change the weights and biases ● After each change, we run the samples again, and repeat, until we get to a minimum cost
  • 15. @tdevinda Many Types of ANNs ● Many types of ANNs exist ● What we tried is a multi-layered perceptron ● Different types are used for different applications ● Convolutional Neural Networks (CNNs): ○ Used for image classifications ○ Uses filters to detect certain features of images ● Recurrent Neural Network (RNNs): ○ Used for speech recognition ○ Contains feedback points from next layers or current layer Many more...