SlideShare ist ein Scribd-Unternehmen logo
1 von 25
Neural Networks
Neural Networks




                  2
Natural Neural Networks
• Signals “move” via electrochemical signals
• The synapses release a chemical transmitter –
  the sum of which can cause a threshold to be
  reached – causing the neuron to “fire”
• Synapses can be inhibitory or excitatory




                                              3
Natural Neural Networks
• We are born with about 100 billion neurons

• A neuron may connect to as many as 100,000
  other neurons




                                               4
Natural Neural Networks
• Many of their ideas still used today e.g.
  – many simple units, “neurons” combine to give
    increased computational power
  – the idea of a threshold




                                                   5
Modelling a Neuron




ini   j
        Wj, iaj • aj      :Activation value of unit j
               •   wj,i   :Weight on link from unit j to unit i
               •   ini    :Weighted sum of inputs to unit i
               •   ai     :Activation value of unit i
               •   g      :Activation function
                                                                  6
Activation Functions




• Stept(x) =   1 if x ≥ t, else 0 threshold=t
• Sign(x) =    +1 if x ≥ 0, else –1
• Sigmoid(x)   =      1/(1+e-x)
                                                7
Building a Neural Network
1. “Select Structure”: Design the way that the
    neurons are interconnected
2. “Select weights” – decide the strengths with
    which the neurons are interconnected
   – weights are selected so get a “good match” to
      a “training set”
   – “training set”: set of inputs and desired
      outputs
   – often use a “learning algorithm”

                                                     8
Basic Neural Networks
• Will first look at simplest networks
• “Feed-forward”
  – Signals travel in one direction through net
  – Net computes a function of the inputs




                                                  9
The First Neural Neural Networks
  X1           2


               2
  X2                            Y

              -1

  X3


 Neurons in a McCulloch-Pitts network are connected by directed, weighted
 paths


                                                                            10
The First Neural Neural Networks
  X1      2


          2
 X2                   Y

         -1

 X3

 If the on weight on a path is positive the path is
 excitatory,
 otherwise it is inhibitory
                                                      11
The First Neural Neural Networks

  X1         2


             2
  X2                       Y

            -1

  X3

The activation of a neuron is binary. That is, the neuron
either fires (activation of one) or does not fire (activation of
zero).
                                                                   12
The First Neural Neural Networks
  X1            2


                2
  X2                               Y

               -1

  X3

For the network shown here the activation function for unit Y is

                              f(y_in) = 1, if y_in >= θ else 0

where    y_in is the total input signal received
         θ is the threshold for Y

                                                                   13
The First Neural Neural Networks
X1          2


             2
X2                            Y

           -1

X3


 Originally, all excitatory connections into a particular neuron have the same
 weight, although different weighted connections can be input to different
 neurons

 Later weights allowed to be arbitrary

                                                                                 14
The First Neural Neural Networks
   X1           2


                2
  X2                              Y

               -1

  X3



Each neuron has a fixed threshold. If
                         the net input into the neuron is
greater than or equal to the threshold, the neuron fires

                                                       15
The First Neural Neural Networks
X1            2


              2
X2                              Y

             -1

X3


The threshold is set such that any non-zero inhibitory input will prevent the neuron
from firing




                                                                                  16
Building Logic Gates

• Computers are built out of “logic gates”

• Use threshold (step) function for activation
  function
   – all activation values are 0 (false) or 1 (true)




                                                       17
The First Neural Neural Networks

                    1
                              AND
      X1

                          Y
                              X1    X2   Y
                                1    1   1
      X2            1
                                1    0   0
           AND Function
                                0    1   0
                                0    0   0


           Threshold(Y) = 2




                                             18
The First Neural Networks
                               OR
X1      2                      X1    X2   Y
                    Y            1    1   1
                                 1    0   1
X2      2
                                 0    1   1
     ANDFunction
      OR Function
                                 0    0   0




            Threshold(Y) = 2




                                              19
Perceptron
         • Synonym for Single-Layer,
           Feed-Forward Network


         • First Studied in the 50’s


         • Other networks were known
           about but the perceptron
           was the only one capable of
           learning and thus all research
           was concentrated in this area




                                       20
Perceptron
         • A single weight only affects
           one output so we can restrict
           our investigations to a model
           as shown on the right
         • Notation can be simpler, i.e.




             O    Step0       j
                                  WjIj




                                     21
What can perceptrons represent?

          AND               XOR
Input 1   0     0   1   1   0     0   1   1
Input 2   0     1   0   1   0     1   0   1
Output    0     0   0   1   0     1   1   0




                                          22
What can perceptrons represent?
                            1,1
                                                                          1,1
     0,1
                                                  0,1




    0,0                           1,0
                                                                                1,0
                                                  0,0
                 AND                                            XOR


•     Functions which can be separated in this way are called Linearly Separable
•     Only linearly separable functions can be represented by a perceptron
•     XOR cannot be represented by a perceptron

                                                                                      23
XOR
•    XOR is not “linearly separable”
    – Cannot be represented by a perceptron
•    What can we do instead?
    1. Convert to logic gates that can be represented by
       perceptrons
    2. Chain together the gates




                                                           24
Single- vs. Multiple-Layers

• Once we chain together the gates then we have “hidden
  layers”
   – layers that are “hidden” from the output lines

• Have just seen that hidden layers allow us to represent XOR
   – Perceptron is single-layer
   – Multiple layers increase the representational power, so
     e.g. can represent XOR

• Generally useful nets have multiple-layers
   – typically 2-4 layers

                                                                25

Weitere ähnliche Inhalte

Was ist angesagt?

Soft computing (ANN and Fuzzy Logic) : Dr. Purnima Pandit
Soft computing (ANN and Fuzzy Logic)  : Dr. Purnima PanditSoft computing (ANN and Fuzzy Logic)  : Dr. Purnima Pandit
Soft computing (ANN and Fuzzy Logic) : Dr. Purnima PanditPurnima Pandit
 
Unification and Lifting
Unification and LiftingUnification and Lifting
Unification and LiftingMegha Sharma
 
Asymptotic notations
Asymptotic notationsAsymptotic notations
Asymptotic notationsNikhil Sharma
 
Bruteforce algorithm
Bruteforce algorithmBruteforce algorithm
Bruteforce algorithmRezwan Siam
 
Multilayer perceptron
Multilayer perceptronMultilayer perceptron
Multilayer perceptronomaraldabash
 
Moore and mealy machines
Moore and mealy machinesMoore and mealy machines
Moore and mealy machinesAYESHA JAVED
 
TOC 1 | Introduction to Theory of Computation
TOC 1 | Introduction to Theory of ComputationTOC 1 | Introduction to Theory of Computation
TOC 1 | Introduction to Theory of ComputationMohammad Imam Hossain
 
Church Turing Thesis
Church Turing ThesisChurch Turing Thesis
Church Turing ThesisHemant Sharma
 
Artificial neural networks
Artificial neural networksArtificial neural networks
Artificial neural networksmadhu sudhakar
 
Introduction to Dynamic Programming, Principle of Optimality
Introduction to Dynamic Programming, Principle of OptimalityIntroduction to Dynamic Programming, Principle of Optimality
Introduction to Dynamic Programming, Principle of OptimalityBhavin Darji
 
Feed forward ,back propagation,gradient descent
Feed forward ,back propagation,gradient descentFeed forward ,back propagation,gradient descent
Feed forward ,back propagation,gradient descentMuhammad Rasel
 
Rules of inference
Rules of inferenceRules of inference
Rules of inferenceharman kaur
 
9. chapter 8 np hard and np complete problems
9. chapter 8   np hard and np complete problems9. chapter 8   np hard and np complete problems
9. chapter 8 np hard and np complete problemsJyotsna Suryadevara
 
Machine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksMachine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksFrancesco Collova'
 
Artificial Neural Networks (ANNs) - XOR - Step-By-Step
Artificial Neural Networks (ANNs) - XOR - Step-By-StepArtificial Neural Networks (ANNs) - XOR - Step-By-Step
Artificial Neural Networks (ANNs) - XOR - Step-By-StepAhmed Gad
 
Cryptography using artificial neural network
Cryptography using artificial neural networkCryptography using artificial neural network
Cryptography using artificial neural networkMahira Banu
 

Was ist angesagt? (20)

Soft computing (ANN and Fuzzy Logic) : Dr. Purnima Pandit
Soft computing (ANN and Fuzzy Logic)  : Dr. Purnima PanditSoft computing (ANN and Fuzzy Logic)  : Dr. Purnima Pandit
Soft computing (ANN and Fuzzy Logic) : Dr. Purnima Pandit
 
Counters
CountersCounters
Counters
 
Unification and Lifting
Unification and LiftingUnification and Lifting
Unification and Lifting
 
Asymptotic notations
Asymptotic notationsAsymptotic notations
Asymptotic notations
 
Bruteforce algorithm
Bruteforce algorithmBruteforce algorithm
Bruteforce algorithm
 
asymptotic notation
asymptotic notationasymptotic notation
asymptotic notation
 
Multilayer perceptron
Multilayer perceptronMultilayer perceptron
Multilayer perceptron
 
Moore and mealy machines
Moore and mealy machinesMoore and mealy machines
Moore and mealy machines
 
Graph coloring
Graph coloringGraph coloring
Graph coloring
 
TOC 1 | Introduction to Theory of Computation
TOC 1 | Introduction to Theory of ComputationTOC 1 | Introduction to Theory of Computation
TOC 1 | Introduction to Theory of Computation
 
Church Turing Thesis
Church Turing ThesisChurch Turing Thesis
Church Turing Thesis
 
AI Lecture 7 (uncertainty)
AI Lecture 7 (uncertainty)AI Lecture 7 (uncertainty)
AI Lecture 7 (uncertainty)
 
Artificial neural networks
Artificial neural networksArtificial neural networks
Artificial neural networks
 
Introduction to Dynamic Programming, Principle of Optimality
Introduction to Dynamic Programming, Principle of OptimalityIntroduction to Dynamic Programming, Principle of Optimality
Introduction to Dynamic Programming, Principle of Optimality
 
Feed forward ,back propagation,gradient descent
Feed forward ,back propagation,gradient descentFeed forward ,back propagation,gradient descent
Feed forward ,back propagation,gradient descent
 
Rules of inference
Rules of inferenceRules of inference
Rules of inference
 
9. chapter 8 np hard and np complete problems
9. chapter 8   np hard and np complete problems9. chapter 8   np hard and np complete problems
9. chapter 8 np hard and np complete problems
 
Machine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksMachine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural Networks
 
Artificial Neural Networks (ANNs) - XOR - Step-By-Step
Artificial Neural Networks (ANNs) - XOR - Step-By-StepArtificial Neural Networks (ANNs) - XOR - Step-By-Step
Artificial Neural Networks (ANNs) - XOR - Step-By-Step
 
Cryptography using artificial neural network
Cryptography using artificial neural networkCryptography using artificial neural network
Cryptography using artificial neural network
 

Andere mochten auch

Neural network
Neural networkNeural network
Neural networkSilicon
 
What is in you
What is in youWhat is in you
What is in youSlideshare
 
Resolution(decision)
Resolution(decision)Resolution(decision)
Resolution(decision)Slideshare
 
Instance based learning
Instance based learningInstance based learning
Instance based learningSlideshare
 
Книги-юбиляры 2013 года
Книги-юбиляры 2013 годаКниги-юбиляры 2013 года
Книги-юбиляры 2013 годаnikola511
 
Report generation
Report generationReport generation
Report generationSlideshare
 
16 Queens Problem - trial 1
16 Queens Problem  - trial 116 Queens Problem  - trial 1
16 Queens Problem - trial 1Slideshare
 
Security in Relational model
Security in Relational modelSecurity in Relational model
Security in Relational modelSlideshare
 
Accessing I/O Devices
Accessing I/O DevicesAccessing I/O Devices
Accessing I/O DevicesSlideshare
 
인공지능 방법론 - 딥러닝 이해하기
인공지능 방법론 - 딥러닝 이해하기인공지능 방법론 - 딥러닝 이해하기
인공지능 방법론 - 딥러닝 이해하기Byoung-Hee Kim
 
Perceptron (neural network)
Perceptron (neural network)Perceptron (neural network)
Perceptron (neural network)EdutechLearners
 
Data preprocessing
Data preprocessingData preprocessing
Data preprocessingSlideshare
 
Crystal report generation in visual studio 2010
Crystal report generation in visual studio 2010Crystal report generation in visual studio 2010
Crystal report generation in visual studio 2010Slideshare
 
Statistical learning
Statistical learningStatistical learning
Statistical learningSlideshare
 
Propositional logic & inference
Propositional logic & inferencePropositional logic & inference
Propositional logic & inferenceSlideshare
 
Major issues in data mining
Major issues in data miningMajor issues in data mining
Major issues in data miningSlideshare
 

Andere mochten auch (20)

Perceptron
PerceptronPerceptron
Perceptron
 
Neural network
Neural networkNeural network
Neural network
 
What is in you
What is in youWhat is in you
What is in you
 
Resolution(decision)
Resolution(decision)Resolution(decision)
Resolution(decision)
 
Instance based learning
Instance based learningInstance based learning
Instance based learning
 
Книги-юбиляры 2013 года
Книги-юбиляры 2013 годаКниги-юбиляры 2013 года
Книги-юбиляры 2013 года
 
Report generation
Report generationReport generation
Report generation
 
16 Queens Problem - trial 1
16 Queens Problem  - trial 116 Queens Problem  - trial 1
16 Queens Problem - trial 1
 
Security in Relational model
Security in Relational modelSecurity in Relational model
Security in Relational model
 
Logic agent
Logic agentLogic agent
Logic agent
 
Unit+i
Unit+iUnit+i
Unit+i
 
Accessing I/O Devices
Accessing I/O DevicesAccessing I/O Devices
Accessing I/O Devices
 
인공지능 방법론 - 딥러닝 이해하기
인공지능 방법론 - 딥러닝 이해하기인공지능 방법론 - 딥러닝 이해하기
인공지능 방법론 - 딥러닝 이해하기
 
Lecture 9 Perceptron
Lecture 9 PerceptronLecture 9 Perceptron
Lecture 9 Perceptron
 
Perceptron (neural network)
Perceptron (neural network)Perceptron (neural network)
Perceptron (neural network)
 
Data preprocessing
Data preprocessingData preprocessing
Data preprocessing
 
Crystal report generation in visual studio 2010
Crystal report generation in visual studio 2010Crystal report generation in visual studio 2010
Crystal report generation in visual studio 2010
 
Statistical learning
Statistical learningStatistical learning
Statistical learning
 
Propositional logic & inference
Propositional logic & inferencePropositional logic & inference
Propositional logic & inference
 
Major issues in data mining
Major issues in data miningMajor issues in data mining
Major issues in data mining
 

Ähnlich wie Neural networks

Neural networks
Neural networksNeural networks
Neural networksSlideshare
 
Lect аі 2 n net p2
Lect аі 2 n net p2Lect аі 2 n net p2
Lect аі 2 n net p2Halyna Melnyk
 
Neural network
Neural networkNeural network
Neural networkmarada0033
 
Arquitecturas Basicas Slides
Arquitecturas Basicas SlidesArquitecturas Basicas Slides
Arquitecturas Basicas SlidesESCOM
 
KAIST 2012 Fall 전자공학개론 6조 발표 PPT
KAIST 2012 Fall 전자공학개론 6조 발표 PPTKAIST 2012 Fall 전자공학개론 6조 발표 PPT
KAIST 2012 Fall 전자공학개론 6조 발표 PPTpjknkda
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural NetworkRenas Rekany
 
Lec1 Inroduction to Neural Network.ppt
Lec1 Inroduction to Neural Network.pptLec1 Inroduction to Neural Network.ppt
Lec1 Inroduction to Neural Network.pptMohamedSadek942403
 
Artificial Neural Network_VCW (1).pptx
Artificial Neural Network_VCW (1).pptxArtificial Neural Network_VCW (1).pptx
Artificial Neural Network_VCW (1).pptxpratik610182
 
Introduction to Neural networks (under graduate course) Lecture 2 of 9
Introduction to Neural networks (under graduate course) Lecture 2 of 9Introduction to Neural networks (under graduate course) Lecture 2 of 9
Introduction to Neural networks (under graduate course) Lecture 2 of 9Randa Elanwar
 
Machine Learning - Introduction to Neural Networks
Machine Learning - Introduction to Neural NetworksMachine Learning - Introduction to Neural Networks
Machine Learning - Introduction to Neural NetworksAndrew Ferlitsch
 
Machine Learning - Neural Networks - Perceptron
Machine Learning - Neural Networks - PerceptronMachine Learning - Neural Networks - Perceptron
Machine Learning - Neural Networks - PerceptronAndrew Ferlitsch
 
Artificial Neural Networks Lect2: Neurobiology & Architectures of ANNS
Artificial Neural Networks Lect2: Neurobiology & Architectures of ANNSArtificial Neural Networks Lect2: Neurobiology & Architectures of ANNS
Artificial Neural Networks Lect2: Neurobiology & Architectures of ANNSMohammed Bennamoun
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Networkssuserab4f3e
 
Deep Learning Tutorial | Deep Learning TensorFlow | Deep Learning With Neural...
Deep Learning Tutorial | Deep Learning TensorFlow | Deep Learning With Neural...Deep Learning Tutorial | Deep Learning TensorFlow | Deep Learning With Neural...
Deep Learning Tutorial | Deep Learning TensorFlow | Deep Learning With Neural...Simplilearn
 

Ähnlich wie Neural networks (20)

Neural networks
Neural networksNeural networks
Neural networks
 
Lect аі 2 n net p2
Lect аі 2 n net p2Lect аі 2 n net p2
Lect аі 2 n net p2
 
Ann ics320 part4
Ann ics320 part4Ann ics320 part4
Ann ics320 part4
 
Neural Networks.pptx
Neural Networks.pptxNeural Networks.pptx
Neural Networks.pptx
 
10-Perceptron.pdf
10-Perceptron.pdf10-Perceptron.pdf
10-Perceptron.pdf
 
Neural networks 1
Neural networks 1Neural networks 1
Neural networks 1
 
Neural network
Neural networkNeural network
Neural network
 
Arquitecturas Basicas Slides
Arquitecturas Basicas SlidesArquitecturas Basicas Slides
Arquitecturas Basicas Slides
 
KAIST 2012 Fall 전자공학개론 6조 발표 PPT
KAIST 2012 Fall 전자공학개론 6조 발표 PPTKAIST 2012 Fall 전자공학개론 6조 발표 PPT
KAIST 2012 Fall 전자공학개론 6조 발표 PPT
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
 
Lec1 Inroduction to Neural Network.ppt
Lec1 Inroduction to Neural Network.pptLec1 Inroduction to Neural Network.ppt
Lec1 Inroduction to Neural Network.ppt
 
Artificial Neural Network_VCW (1).pptx
Artificial Neural Network_VCW (1).pptxArtificial Neural Network_VCW (1).pptx
Artificial Neural Network_VCW (1).pptx
 
Introduction to Neural networks (under graduate course) Lecture 2 of 9
Introduction to Neural networks (under graduate course) Lecture 2 of 9Introduction to Neural networks (under graduate course) Lecture 2 of 9
Introduction to Neural networks (under graduate course) Lecture 2 of 9
 
Machine Learning - Introduction to Neural Networks
Machine Learning - Introduction to Neural NetworksMachine Learning - Introduction to Neural Networks
Machine Learning - Introduction to Neural Networks
 
Machine Learning - Neural Networks - Perceptron
Machine Learning - Neural Networks - PerceptronMachine Learning - Neural Networks - Perceptron
Machine Learning - Neural Networks - Perceptron
 
Artificial Neural Networks Lect2: Neurobiology & Architectures of ANNS
Artificial Neural Networks Lect2: Neurobiology & Architectures of ANNSArtificial Neural Networks Lect2: Neurobiology & Architectures of ANNS
Artificial Neural Networks Lect2: Neurobiology & Architectures of ANNS
 
Lec10
Lec10Lec10
Lec10
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
 
Deep Learning Tutorial | Deep Learning TensorFlow | Deep Learning With Neural...
Deep Learning Tutorial | Deep Learning TensorFlow | Deep Learning With Neural...Deep Learning Tutorial | Deep Learning TensorFlow | Deep Learning With Neural...
Deep Learning Tutorial | Deep Learning TensorFlow | Deep Learning With Neural...
 
Lec-02.pdf
Lec-02.pdfLec-02.pdf
Lec-02.pdf
 

Mehr von Slideshare

Entity Relationship Model
Entity Relationship ModelEntity Relationship Model
Entity Relationship ModelSlideshare
 
Logical reasoning 21.1.13
Logical reasoning 21.1.13Logical reasoning 21.1.13
Logical reasoning 21.1.13Slideshare
 
Statistical learning
Statistical learningStatistical learning
Statistical learningSlideshare
 
Reinforcement learning 7313
Reinforcement learning 7313Reinforcement learning 7313
Reinforcement learning 7313Slideshare
 
Logical reasoning
Logical reasoning Logical reasoning
Logical reasoning Slideshare
 
Instance based learning
Instance based learningInstance based learning
Instance based learningSlideshare
 
Input & output devices
Input & output devicesInput & output devices
Input & output devicesSlideshare
 
16 queens problem - trial 2
16 queens problem - trial 216 queens problem - trial 2
16 queens problem - trial 2Slideshare
 
Basic Processing Unit
Basic Processing UnitBasic Processing Unit
Basic Processing UnitSlideshare
 
Cache performance considerations
Cache performance considerationsCache performance considerations
Cache performance considerationsSlideshare
 
Memory management
Memory managementMemory management
Memory managementSlideshare
 
Secondary storage devices
Secondary storage devices Secondary storage devices
Secondary storage devices Slideshare
 
Magnetic tape system
Magnetic tape systemMagnetic tape system
Magnetic tape systemSlideshare
 

Mehr von Slideshare (16)

Trigger
TriggerTrigger
Trigger
 
Entity Relationship Model
Entity Relationship ModelEntity Relationship Model
Entity Relationship Model
 
OLAP
OLAPOLAP
OLAP
 
Logical reasoning 21.1.13
Logical reasoning 21.1.13Logical reasoning 21.1.13
Logical reasoning 21.1.13
 
Statistical learning
Statistical learningStatistical learning
Statistical learning
 
Reinforcement learning 7313
Reinforcement learning 7313Reinforcement learning 7313
Reinforcement learning 7313
 
Logical reasoning
Logical reasoning Logical reasoning
Logical reasoning
 
Instance based learning
Instance based learningInstance based learning
Instance based learning
 
Input & output devices
Input & output devicesInput & output devices
Input & output devices
 
16 queens problem - trial 2
16 queens problem - trial 216 queens problem - trial 2
16 queens problem - trial 2
 
Basic Processing Unit
Basic Processing UnitBasic Processing Unit
Basic Processing Unit
 
Cache performance considerations
Cache performance considerationsCache performance considerations
Cache performance considerations
 
Cachememory
CachememoryCachememory
Cachememory
 
Memory management
Memory managementMemory management
Memory management
 
Secondary storage devices
Secondary storage devices Secondary storage devices
Secondary storage devices
 
Magnetic tape system
Magnetic tape systemMagnetic tape system
Magnetic tape system
 

Kürzlich hochgeladen

Q-Factor General Quiz-7th April 2024, Quiz Club NITW
Q-Factor General Quiz-7th April 2024, Quiz Club NITWQ-Factor General Quiz-7th April 2024, Quiz Club NITW
Q-Factor General Quiz-7th April 2024, Quiz Club NITWQuiz Club NITW
 
Using Grammatical Signals Suitable to Patterns of Idea Development
Using Grammatical Signals Suitable to Patterns of Idea DevelopmentUsing Grammatical Signals Suitable to Patterns of Idea Development
Using Grammatical Signals Suitable to Patterns of Idea Developmentchesterberbo7
 
Grade 9 Quarter 4 Dll Grade 9 Quarter 4 DLL.pdf
Grade 9 Quarter 4 Dll Grade 9 Quarter 4 DLL.pdfGrade 9 Quarter 4 Dll Grade 9 Quarter 4 DLL.pdf
Grade 9 Quarter 4 Dll Grade 9 Quarter 4 DLL.pdfJemuel Francisco
 
Active Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfActive Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfPatidar M
 
Unraveling Hypertext_ Analyzing Postmodern Elements in Literature.pptx
Unraveling Hypertext_ Analyzing  Postmodern Elements in  Literature.pptxUnraveling Hypertext_ Analyzing  Postmodern Elements in  Literature.pptx
Unraveling Hypertext_ Analyzing Postmodern Elements in Literature.pptxDhatriParmar
 
How to Make a Duplicate of Your Odoo 17 Database
How to Make a Duplicate of Your Odoo 17 DatabaseHow to Make a Duplicate of Your Odoo 17 Database
How to Make a Duplicate of Your Odoo 17 DatabaseCeline George
 
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...DhatriParmar
 
Expanded definition: technical and operational
Expanded definition: technical and operationalExpanded definition: technical and operational
Expanded definition: technical and operationalssuser3e220a
 
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITWQ-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITWQuiz Club NITW
 
Team Lead Succeed – Helping you and your team achieve high-performance teamwo...
Team Lead Succeed – Helping you and your team achieve high-performance teamwo...Team Lead Succeed – Helping you and your team achieve high-performance teamwo...
Team Lead Succeed – Helping you and your team achieve high-performance teamwo...Association for Project Management
 
Mythology Quiz-4th April 2024, Quiz Club NITW
Mythology Quiz-4th April 2024, Quiz Club NITWMythology Quiz-4th April 2024, Quiz Club NITW
Mythology Quiz-4th April 2024, Quiz Club NITWQuiz Club NITW
 
31 ĐỀ THI THỬ VÀO LỚP 10 - TIẾNG ANH - FORM MỚI 2025 - 40 CÂU HỎI - BÙI VĂN V...
31 ĐỀ THI THỬ VÀO LỚP 10 - TIẾNG ANH - FORM MỚI 2025 - 40 CÂU HỎI - BÙI VĂN V...31 ĐỀ THI THỬ VÀO LỚP 10 - TIẾNG ANH - FORM MỚI 2025 - 40 CÂU HỎI - BÙI VĂN V...
31 ĐỀ THI THỬ VÀO LỚP 10 - TIẾNG ANH - FORM MỚI 2025 - 40 CÂU HỎI - BÙI VĂN V...Nguyen Thanh Tu Collection
 
ClimART Action | eTwinning Project
ClimART Action    |    eTwinning ProjectClimART Action    |    eTwinning Project
ClimART Action | eTwinning Projectjordimapav
 
week 1 cookery 8 fourth - quarter .pptx
week 1 cookery 8  fourth  -  quarter .pptxweek 1 cookery 8  fourth  -  quarter .pptx
week 1 cookery 8 fourth - quarter .pptxJonalynLegaspi2
 
Transaction Management in Database Management System
Transaction Management in Database Management SystemTransaction Management in Database Management System
Transaction Management in Database Management SystemChristalin Nelson
 
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptxDecoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptxDhatriParmar
 
Measures of Position DECILES for ungrouped data
Measures of Position DECILES for ungrouped dataMeasures of Position DECILES for ungrouped data
Measures of Position DECILES for ungrouped dataBabyAnnMotar
 
Concurrency Control in Database Management system
Concurrency Control in Database Management systemConcurrency Control in Database Management system
Concurrency Control in Database Management systemChristalin Nelson
 
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptxINTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptxHumphrey A Beña
 

Kürzlich hochgeladen (20)

Q-Factor General Quiz-7th April 2024, Quiz Club NITW
Q-Factor General Quiz-7th April 2024, Quiz Club NITWQ-Factor General Quiz-7th April 2024, Quiz Club NITW
Q-Factor General Quiz-7th April 2024, Quiz Club NITW
 
Using Grammatical Signals Suitable to Patterns of Idea Development
Using Grammatical Signals Suitable to Patterns of Idea DevelopmentUsing Grammatical Signals Suitable to Patterns of Idea Development
Using Grammatical Signals Suitable to Patterns of Idea Development
 
Grade 9 Quarter 4 Dll Grade 9 Quarter 4 DLL.pdf
Grade 9 Quarter 4 Dll Grade 9 Quarter 4 DLL.pdfGrade 9 Quarter 4 Dll Grade 9 Quarter 4 DLL.pdf
Grade 9 Quarter 4 Dll Grade 9 Quarter 4 DLL.pdf
 
Active Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdfActive Learning Strategies (in short ALS).pdf
Active Learning Strategies (in short ALS).pdf
 
Unraveling Hypertext_ Analyzing Postmodern Elements in Literature.pptx
Unraveling Hypertext_ Analyzing  Postmodern Elements in  Literature.pptxUnraveling Hypertext_ Analyzing  Postmodern Elements in  Literature.pptx
Unraveling Hypertext_ Analyzing Postmodern Elements in Literature.pptx
 
How to Make a Duplicate of Your Odoo 17 Database
How to Make a Duplicate of Your Odoo 17 DatabaseHow to Make a Duplicate of Your Odoo 17 Database
How to Make a Duplicate of Your Odoo 17 Database
 
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...
Blowin' in the Wind of Caste_ Bob Dylan's Song as a Catalyst for Social Justi...
 
Expanded definition: technical and operational
Expanded definition: technical and operationalExpanded definition: technical and operational
Expanded definition: technical and operational
 
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITWQ-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
Q-Factor HISPOL Quiz-6th April 2024, Quiz Club NITW
 
Team Lead Succeed – Helping you and your team achieve high-performance teamwo...
Team Lead Succeed – Helping you and your team achieve high-performance teamwo...Team Lead Succeed – Helping you and your team achieve high-performance teamwo...
Team Lead Succeed – Helping you and your team achieve high-performance teamwo...
 
Mythology Quiz-4th April 2024, Quiz Club NITW
Mythology Quiz-4th April 2024, Quiz Club NITWMythology Quiz-4th April 2024, Quiz Club NITW
Mythology Quiz-4th April 2024, Quiz Club NITW
 
31 ĐỀ THI THỬ VÀO LỚP 10 - TIẾNG ANH - FORM MỚI 2025 - 40 CÂU HỎI - BÙI VĂN V...
31 ĐỀ THI THỬ VÀO LỚP 10 - TIẾNG ANH - FORM MỚI 2025 - 40 CÂU HỎI - BÙI VĂN V...31 ĐỀ THI THỬ VÀO LỚP 10 - TIẾNG ANH - FORM MỚI 2025 - 40 CÂU HỎI - BÙI VĂN V...
31 ĐỀ THI THỬ VÀO LỚP 10 - TIẾNG ANH - FORM MỚI 2025 - 40 CÂU HỎI - BÙI VĂN V...
 
ClimART Action | eTwinning Project
ClimART Action    |    eTwinning ProjectClimART Action    |    eTwinning Project
ClimART Action | eTwinning Project
 
week 1 cookery 8 fourth - quarter .pptx
week 1 cookery 8  fourth  -  quarter .pptxweek 1 cookery 8  fourth  -  quarter .pptx
week 1 cookery 8 fourth - quarter .pptx
 
Transaction Management in Database Management System
Transaction Management in Database Management SystemTransaction Management in Database Management System
Transaction Management in Database Management System
 
Faculty Profile prashantha K EEE dept Sri Sairam college of Engineering
Faculty Profile prashantha K EEE dept Sri Sairam college of EngineeringFaculty Profile prashantha K EEE dept Sri Sairam college of Engineering
Faculty Profile prashantha K EEE dept Sri Sairam college of Engineering
 
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptxDecoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
Decoding the Tweet _ Practical Criticism in the Age of Hashtag.pptx
 
Measures of Position DECILES for ungrouped data
Measures of Position DECILES for ungrouped dataMeasures of Position DECILES for ungrouped data
Measures of Position DECILES for ungrouped data
 
Concurrency Control in Database Management system
Concurrency Control in Database Management systemConcurrency Control in Database Management system
Concurrency Control in Database Management system
 
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptxINTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
INTRODUCTION TO CATHOLIC CHRISTOLOGY.pptx
 

Neural networks

  • 3. Natural Neural Networks • Signals “move” via electrochemical signals • The synapses release a chemical transmitter – the sum of which can cause a threshold to be reached – causing the neuron to “fire” • Synapses can be inhibitory or excitatory 3
  • 4. Natural Neural Networks • We are born with about 100 billion neurons • A neuron may connect to as many as 100,000 other neurons 4
  • 5. Natural Neural Networks • Many of their ideas still used today e.g. – many simple units, “neurons” combine to give increased computational power – the idea of a threshold 5
  • 6. Modelling a Neuron ini j Wj, iaj • aj :Activation value of unit j • wj,i :Weight on link from unit j to unit i • ini :Weighted sum of inputs to unit i • ai :Activation value of unit i • g :Activation function 6
  • 7. Activation Functions • Stept(x) = 1 if x ≥ t, else 0 threshold=t • Sign(x) = +1 if x ≥ 0, else –1 • Sigmoid(x) = 1/(1+e-x) 7
  • 8. Building a Neural Network 1. “Select Structure”: Design the way that the neurons are interconnected 2. “Select weights” – decide the strengths with which the neurons are interconnected – weights are selected so get a “good match” to a “training set” – “training set”: set of inputs and desired outputs – often use a “learning algorithm” 8
  • 9. Basic Neural Networks • Will first look at simplest networks • “Feed-forward” – Signals travel in one direction through net – Net computes a function of the inputs 9
  • 10. The First Neural Neural Networks X1 2 2 X2 Y -1 X3 Neurons in a McCulloch-Pitts network are connected by directed, weighted paths 10
  • 11. The First Neural Neural Networks X1 2 2 X2 Y -1 X3 If the on weight on a path is positive the path is excitatory, otherwise it is inhibitory 11
  • 12. The First Neural Neural Networks X1 2 2 X2 Y -1 X3 The activation of a neuron is binary. That is, the neuron either fires (activation of one) or does not fire (activation of zero). 12
  • 13. The First Neural Neural Networks X1 2 2 X2 Y -1 X3 For the network shown here the activation function for unit Y is f(y_in) = 1, if y_in >= θ else 0 where y_in is the total input signal received θ is the threshold for Y 13
  • 14. The First Neural Neural Networks X1 2 2 X2 Y -1 X3 Originally, all excitatory connections into a particular neuron have the same weight, although different weighted connections can be input to different neurons Later weights allowed to be arbitrary 14
  • 15. The First Neural Neural Networks X1 2 2 X2 Y -1 X3 Each neuron has a fixed threshold. If the net input into the neuron is greater than or equal to the threshold, the neuron fires 15
  • 16. The First Neural Neural Networks X1 2 2 X2 Y -1 X3 The threshold is set such that any non-zero inhibitory input will prevent the neuron from firing 16
  • 17. Building Logic Gates • Computers are built out of “logic gates” • Use threshold (step) function for activation function – all activation values are 0 (false) or 1 (true) 17
  • 18. The First Neural Neural Networks 1 AND X1 Y X1 X2 Y 1 1 1 X2 1 1 0 0 AND Function 0 1 0 0 0 0 Threshold(Y) = 2 18
  • 19. The First Neural Networks OR X1 2 X1 X2 Y Y 1 1 1 1 0 1 X2 2 0 1 1 ANDFunction OR Function 0 0 0 Threshold(Y) = 2 19
  • 20. Perceptron • Synonym for Single-Layer, Feed-Forward Network • First Studied in the 50’s • Other networks were known about but the perceptron was the only one capable of learning and thus all research was concentrated in this area 20
  • 21. Perceptron • A single weight only affects one output so we can restrict our investigations to a model as shown on the right • Notation can be simpler, i.e. O Step0 j WjIj 21
  • 22. What can perceptrons represent? AND XOR Input 1 0 0 1 1 0 0 1 1 Input 2 0 1 0 1 0 1 0 1 Output 0 0 0 1 0 1 1 0 22
  • 23. What can perceptrons represent? 1,1 1,1 0,1 0,1 0,0 1,0 1,0 0,0 AND XOR • Functions which can be separated in this way are called Linearly Separable • Only linearly separable functions can be represented by a perceptron • XOR cannot be represented by a perceptron 23
  • 24. XOR • XOR is not “linearly separable” – Cannot be represented by a perceptron • What can we do instead? 1. Convert to logic gates that can be represented by perceptrons 2. Chain together the gates 24
  • 25. Single- vs. Multiple-Layers • Once we chain together the gates then we have “hidden layers” – layers that are “hidden” from the output lines • Have just seen that hidden layers allow us to represent XOR – Perceptron is single-layer – Multiple layers increase the representational power, so e.g. can represent XOR • Generally useful nets have multiple-layers – typically 2-4 layers 25