SlideShare uma empresa Scribd logo
1 de 35
UNIT I

   Introduction To Neural Networks
   Biological Neural Networks
   Characteristics of Neural Networks
   Models of Neurons
What is Neural Network?

   An Artificial Neural Network (ANN) is an
    information processing paradigm that is
    inspired by the way biological nervous
    systems, such as the brain, to process
    information.

    An artificial neural network is a system
    based on the operation of biological
    neural networks, in other words, is an
    emulation of biological neural system.
Why learn Neural Networks?

   Neural networks, with their remarkable ability
    to derive meaning from complicated or
    imprecise data, can be used to extract
    patterns and detect trends that are too
    complex to be noticed by either humans or
    other computer techniques.

   A trained neural network can be thought of
    as an "expert" in the category of information
    it has been given to analyze.
Advantages

   Adaptive learning: An ability to learn how to do tasks
    based on the data given for training or initial
    experience.
   Self-Organization: An ANN can create its own
    organization or representation of the information it
    receives during learning time.
   Real Time Operation: ANN computations may be
    carried out in parallel, and special hardware devices
    are being designed and manufactured which take
    advantage of this capability.
   Fault Tolerance via Redundant Information Coding:
    Partial destruction of a network leads to the
    corresponding degradation of performance. However,
    some network capabilities may be retained even with
    major network damage.
Neural networks versus conventional
     computers
   Conventional computers use an algorithmic approach
    i.e. the computer follows a set of instructions in order to
    solve a problem.

   Neural networks process information in a similar way
    the human brain does. The network is composed of a
    large number of highly interconnected processing
    elements (neurons) working in parallel to solve a
    specific problem. Neural networks learn by
    example. They cannot be programmed to perform a
    specific task.

   Neural networks and conventional algorithmic
    computers are not in competition but complement
    each other.
Biological Neural Networks

   A neural network is mans crude way
    of trying to simulate the brain
    electronically. So to understand how
    a neural net works we first must
    have a look at how the human brain
    works.
Neuron

   The human brain contains about 10 billion
    nerve cells, or neurons.

   Each neuron is connected to thousands of
    other neurons and communicates with them
    via electrochemical signals.

   Signals coming into the neuron are received
    via junctions called synapses, these in turn
    are located at the end of branches of the
    neuron cell called dendrites.
Characteristics of Neural Network

   parallel, distributed information
    processing
   high degree of connectivity among basic
    units
   connections are modifiable based on
    experience
   learning is a constant process, and
    usually unsupervised
   learning is based only on local information
   performance degrades gracefully if some
    units are removed
Summary

   Neural Networks exhibits brain like
    behaviors like:
       Learning
       Association
       Categorization
       Generalization
       Feature Extraction
       Optimization
       Noise Immunity
Models of Neuron

   An artificial neuron is simply an
    electronically modeled biological neuron.
    How many neurons are used depends on
    the task at hand.
Mathematical Model
McCulloch Pitts Model

   The early model of an artificial
    neuron is introduced by Warren
    McCulloch a neuroscientist and
    Walter Pitts a logician in 1943.

   The McCulloch-Pitts neural model is
    also known as linear threshold gate.
An Example


Object      Purple?   Round?   Eat?

Blueberry   1         1        1


Golf Ball   0         1        0


Banana      0         0        0
Problems
   Set the threshold so that the bird
    eats any object that is round or
    purple or both.

   Set the threshold so that the bird
    eats all the objects.
Excitatory & Inhibitory
   The signals are called excitatory
    because they excite the neuron toward
    possibly sending its own signal.

   So as the neuron receives more and
    more excitatory signals, it gets more
    and more excited, until the threshold
    is reached, and the neuron sends out
    its own signal.
   The Inhibitory signals have the effect of
    inhibiting the neuron from sending a signal.

   When a neuron receives an inhibitory signal, it
    becomes less excited, and so it takes more
    excitatory signals to reach the neuron's
    threshold.

   In effect, inhibitory signals subtract from the
    total of the excitatory signals, making the
    neuron more relaxed, and moving the neuron
    away from its threshold.
Perceptron

   A perceptron which was introduced by
    Frank Rosenblatt in 1958.
   Essentially the perceptron is an MCP
    neuron where the inputs are first
    passed through some "preprocessors"
    which are called association units.
   These association units detect the
    presence of certain specific features in
    the inputs.
Perceptron

   In essence an association unit is
    also an MCP neuron which is 1 if a
    single specific pattern of inputs is
    received, and it is 0 for all other
    possible patterns of inputs.
Adaline (Adaptive linear element)
   An important generalization of the perceptron
    training algorithm.

   It was presented by Widrow and Hoff as the
    'least mean square' (LMS) learning
    procedure, also known as the delta rule.

   The main functional difference with the
    Perceptron training rule is the way the output
    of the system is used in the learning rule.
Neural Network Topologies

   The arrangements of the processing
    units, connections, and pattern input /
    output is referred to as topology.

   Connections can be made in two ways
    Interlayer
    Intralayer
Feedforward & Feedback

   Feed-forward ANNs allow signals to travel
    one way only; from input to output.

   There is no feedback (loops) i.e. the output
    of any layer does not affect that same layer.

   They are extensively used in pattern
    recognition. This type of organization is also
    referred to as bottom-up or top-down.
Feedforward Network Diagram
Basic Learning Rules

   Learning: The ability of the neural network
    (NN) to learn from its environment and to
    improve its performance through learning.

   Learning is a process by which the free
    parameters of a neural network are adapted
    through a process of stimulation by the
    environment in which the network is
    embedded.

   The type of the learning is determined by the
    manner in which the parameter changes
    take place.
Learning Rules

   Hebb’s Law

   Perceptron Learning Law

   Delta Learning Law

   Widrow and Hoff LMS Learning Law

   Correlation Learning Law

   Instar ( Winner – take – all)

   Outstar Learning Law
Supervised Learning
   During the training session of neural
    network, an input stimulus is applied
    that results in output response.

   This response is compared with an
    priori desired output signal, the target
    response.

   If the actual response differs from the
    target response, the neural network
    generates an error signal.
   This error signal is used to calculate the
    adjustments that should be made to
    network’s synaptic weights so that the
    actual o/p matches the target output.

   This error minimization process requires a
    special circuit known as supervisor or
    teacher, hence the name Supervised
    learning.

   A neural net is said to learn supervised, if
    the desired output is already known.
Unsupervised Learning

   Unsupervised learning does not require a
    teacher; that is there is no target output.

   During the training session, the neural net
    receives at its input many different
    excitations or input patterns.

   The neural net arbitrarily organizes the
    patterns into categories.
   When the stimulus is applied later, the neural
    net provides an output response indicating
    the class to which the stimulus belongs.

   If a class cannot be found for the input
    stimulus, a new class is generated.

   Even though unsupervised learning does not
    require a teacher, it requires guidelines to
    determine how it will form groups.
Reinforced Learning
   Reinforced learning requires one or more
    neurons at the output layer and a teacher.

   Unlike supervised learning, teacher does not
    indicate how close the actual output is to the
    target output but whether the actual output
    is the same with target output or not.

   The teacher does not present the target
    output to the network, but presents only a
    pass/fail indication.
Contd..

   The error signal generated during the
    training session is binary: pass or fail.

   If the teachers indication is bad, the
    network readjusts its parameters and tries
    again and again until it gets its output
    response right.

   There is no clear indication if the output
    response is moving in the right direction or
    how close it is to the correct response it is.
Competitive Learning

   It is another form of supervised learning
    that is distinctive because of its
    characteristics operation and
    architecture.

   Several neurons are at the output layer.
    When an input stimulus is applied, each
    output neuron competes with the others
    to produce the closest output signal to
    the target.
Contd..
   This output becomes the dominant one,
    and the other outputs cease producing an
    output signal for that stimulus.

   For another stimulus, another output
    neuron becomes the dominant one.

   Thus each output neuron is trained to
    respond to a different input stimulus.

Mais conteúdo relacionado

Mais procurados

Artificial Neural Network (draft)
Artificial Neural Network (draft)Artificial Neural Network (draft)
Artificial Neural Network (draft)James Boulie
 
Artificial Neural Networks Lect1: Introduction & neural computation
Artificial Neural Networks Lect1: Introduction & neural computationArtificial Neural Networks Lect1: Introduction & neural computation
Artificial Neural Networks Lect1: Introduction & neural computationMohammed Bennamoun
 
Artifical Neural Network and its applications
Artifical Neural Network and its applicationsArtifical Neural Network and its applications
Artifical Neural Network and its applicationsSangeeta Tiwari
 
Artificial neural networks and its applications
Artificial neural networks and its applications Artificial neural networks and its applications
Artificial neural networks and its applications PoojaKoshti2
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural NetworkPratik Aggarwal
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural NetworkPrakash K
 
Artificial neural networks (2)
Artificial neural networks (2)Artificial neural networks (2)
Artificial neural networks (2)sai anjaneya
 
Neural networks
Neural networksNeural networks
Neural networksBasil John
 
Artificial neural networks and its application
Artificial neural networks and its applicationArtificial neural networks and its application
Artificial neural networks and its applicationHưng Đặng
 
Neural network final NWU 4.3 Graphics Course
Neural network final NWU 4.3 Graphics CourseNeural network final NWU 4.3 Graphics Course
Neural network final NWU 4.3 Graphics CourseMohaiminur Rahman
 
what is neural network....???
what is neural network....???what is neural network....???
what is neural network....???Adii Shah
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural NetworkAtul Krishna
 
Artificial neural network model & hidden layers in multilayer artificial neur...
Artificial neural network model & hidden layers in multilayer artificial neur...Artificial neural network model & hidden layers in multilayer artificial neur...
Artificial neural network model & hidden layers in multilayer artificial neur...Muhammad Ishaq
 

Mais procurados (20)

Artificial Neural Network (draft)
Artificial Neural Network (draft)Artificial Neural Network (draft)
Artificial Neural Network (draft)
 
Neural Networks
Neural NetworksNeural Networks
Neural Networks
 
Artificial Neural Networks Lect1: Introduction & neural computation
Artificial Neural Networks Lect1: Introduction & neural computationArtificial Neural Networks Lect1: Introduction & neural computation
Artificial Neural Networks Lect1: Introduction & neural computation
 
Artifical Neural Network and its applications
Artifical Neural Network and its applicationsArtifical Neural Network and its applications
Artifical Neural Network and its applications
 
Neural
NeuralNeural
Neural
 
Artificial neural networks and its applications
Artificial neural networks and its applications Artificial neural networks and its applications
Artificial neural networks and its applications
 
neural networks
neural networksneural networks
neural networks
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
 
Neural network
Neural networkNeural network
Neural network
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
 
Neural Networks
Neural NetworksNeural Networks
Neural Networks
 
Artificial neural networks (2)
Artificial neural networks (2)Artificial neural networks (2)
Artificial neural networks (2)
 
Neural networks
Neural networksNeural networks
Neural networks
 
Artificial neural networks and its application
Artificial neural networks and its applicationArtificial neural networks and its application
Artificial neural networks and its application
 
Neural network final NWU 4.3 Graphics Course
Neural network final NWU 4.3 Graphics CourseNeural network final NWU 4.3 Graphics Course
Neural network final NWU 4.3 Graphics Course
 
Neural network
Neural networkNeural network
Neural network
 
what is neural network....???
what is neural network....???what is neural network....???
what is neural network....???
 
Artifical Neural Network
Artifical Neural NetworkArtifical Neural Network
Artifical Neural Network
 
Artificial Neural Network
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
 
Artificial neural network model & hidden layers in multilayer artificial neur...
Artificial neural network model & hidden layers in multilayer artificial neur...Artificial neural network model & hidden layers in multilayer artificial neur...
Artificial neural network model & hidden layers in multilayer artificial neur...
 

Destaque

Counterpropagation NETWORK
Counterpropagation NETWORKCounterpropagation NETWORK
Counterpropagation NETWORKESCOM
 
Artificial Neural Networks Lect3: Neural Network Learning rules
Artificial Neural Networks Lect3: Neural Network Learning rulesArtificial Neural Networks Lect3: Neural Network Learning rules
Artificial Neural Networks Lect3: Neural Network Learning rulesMohammed Bennamoun
 
Neural networks...
Neural networks...Neural networks...
Neural networks...Molly Chugh
 
Adaline madaline
Adaline madalineAdaline madaline
Adaline madalineNagarajan
 
Artificial neural network
Artificial neural networkArtificial neural network
Artificial neural networkDEEPASHRI HK
 
Self Organinising neural networks
Self Organinising  neural networksSelf Organinising  neural networks
Self Organinising neural networksESCOM
 
Radial Basis Function Network (RBFN)
Radial Basis Function Network (RBFN)Radial Basis Function Network (RBFN)
Radial Basis Function Network (RBFN)ahmad haidaroh
 
Neural networks
Neural networksNeural networks
Neural networksSlideshare
 
Counter propagation Network
Counter propagation NetworkCounter propagation Network
Counter propagation NetworkAkshay Dhole
 
Radial basis function network ppt bySheetal,Samreen and Dhanashri
Radial basis function network ppt bySheetal,Samreen and DhanashriRadial basis function network ppt bySheetal,Samreen and Dhanashri
Radial basis function network ppt bySheetal,Samreen and Dhanashrisheetal katkar
 
Control Strategies in AI
Control Strategies in AIControl Strategies in AI
Control Strategies in AIAmey Kerkar
 
Neural Networks: Radial Bases Functions (RBF)
Neural Networks: Radial Bases Functions (RBF)Neural Networks: Radial Bases Functions (RBF)
Neural Networks: Radial Bases Functions (RBF)Mostafa G. M. Mostafa
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial IntelligenceBise Mond
 
weak slot and filler structure
weak slot and filler structureweak slot and filler structure
weak slot and filler structureAmey Kerkar
 
Counterpropagation NETWORK
Counterpropagation NETWORKCounterpropagation NETWORK
Counterpropagation NETWORKESCOM
 
Associative memory 14208
Associative memory 14208Associative memory 14208
Associative memory 14208Ameer Mehmood
 

Destaque (20)

Counterpropagation NETWORK
Counterpropagation NETWORKCounterpropagation NETWORK
Counterpropagation NETWORK
 
Artificial Neural Networks Lect3: Neural Network Learning rules
Artificial Neural Networks Lect3: Neural Network Learning rulesArtificial Neural Networks Lect3: Neural Network Learning rules
Artificial Neural Networks Lect3: Neural Network Learning rules
 
Neural networks...
Neural networks...Neural networks...
Neural networks...
 
Adaline madaline
Adaline madalineAdaline madaline
Adaline madaline
 
Soft computing
Soft computingSoft computing
Soft computing
 
Artificial neural network
Artificial neural networkArtificial neural network
Artificial neural network
 
Self Organinising neural networks
Self Organinising  neural networksSelf Organinising  neural networks
Self Organinising neural networks
 
Radial Basis Function
Radial Basis FunctionRadial Basis Function
Radial Basis Function
 
Radial Basis Function Network (RBFN)
Radial Basis Function Network (RBFN)Radial Basis Function Network (RBFN)
Radial Basis Function Network (RBFN)
 
Neural networks
Neural networksNeural networks
Neural networks
 
Counter propagation Network
Counter propagation NetworkCounter propagation Network
Counter propagation Network
 
Neural networks introduction
Neural networks introductionNeural networks introduction
Neural networks introduction
 
Radial basis function network ppt bySheetal,Samreen and Dhanashri
Radial basis function network ppt bySheetal,Samreen and DhanashriRadial basis function network ppt bySheetal,Samreen and Dhanashri
Radial basis function network ppt bySheetal,Samreen and Dhanashri
 
Control Strategies in AI
Control Strategies in AIControl Strategies in AI
Control Strategies in AI
 
Neural Networks: Radial Bases Functions (RBF)
Neural Networks: Radial Bases Functions (RBF)Neural Networks: Radial Bases Functions (RBF)
Neural Networks: Radial Bases Functions (RBF)
 
Artificial Intelligence
Artificial IntelligenceArtificial Intelligence
Artificial Intelligence
 
weak slot and filler structure
weak slot and filler structureweak slot and filler structure
weak slot and filler structure
 
Counterpropagation NETWORK
Counterpropagation NETWORKCounterpropagation NETWORK
Counterpropagation NETWORK
 
Propositional logic
Propositional logicPropositional logic
Propositional logic
 
Associative memory 14208
Associative memory 14208Associative memory 14208
Associative memory 14208
 

Semelhante a Introduction to Neural Networks in 40 Characters

Artificial Neural Network in Medical Diagnosis
Artificial Neural Network in Medical DiagnosisArtificial Neural Network in Medical Diagnosis
Artificial Neural Network in Medical DiagnosisAdityendra Kumar Singh
 
Neural networks are parallel computing devices.docx.pdf
Neural networks are parallel computing devices.docx.pdfNeural networks are parallel computing devices.docx.pdf
Neural networks are parallel computing devices.docx.pdfneelamsanjeevkumar
 
Neural Network
Neural NetworkNeural Network
Neural NetworkSayyed Z
 
Neuralnetwork 101222074552-phpapp02
Neuralnetwork 101222074552-phpapp02Neuralnetwork 101222074552-phpapp02
Neuralnetwork 101222074552-phpapp02Deepu Gupta
 
Neural networks of artificial intelligence
Neural networks of artificial  intelligenceNeural networks of artificial  intelligence
Neural networks of artificial intelligencealldesign
 
Soft Computing-173101
Soft Computing-173101Soft Computing-173101
Soft Computing-173101AMIT KUMAR
 
Introduction to Artificial Neural Networks
Introduction to Artificial Neural Networks Introduction to Artificial Neural Networks
Introduction to Artificial Neural Networks MuhammadMir92
 
Artificial Neural Network report
Artificial Neural Network reportArtificial Neural Network report
Artificial Neural Network reportAnjali Agrawal
 
neural networks
 neural networks neural networks
neural networksjoshiblog
 
Artificial Neural Network seminar presentation using ppt.
Artificial Neural Network seminar presentation using ppt.Artificial Neural Network seminar presentation using ppt.
Artificial Neural Network seminar presentation using ppt.Mohd Faiz
 
Neural net NWU 4.3 Graphics Course
Neural net NWU 4.3 Graphics CourseNeural net NWU 4.3 Graphics Course
Neural net NWU 4.3 Graphics CourseMohaiminur Rahman
 
SujanKhamrui_28100119050.pptx
SujanKhamrui_28100119050.pptxSujanKhamrui_28100119050.pptx
SujanKhamrui_28100119050.pptxPrakasBhowmik
 

Semelhante a Introduction to Neural Networks in 40 Characters (20)

Artificial Neural Network in Medical Diagnosis
Artificial Neural Network in Medical DiagnosisArtificial Neural Network in Medical Diagnosis
Artificial Neural Network in Medical Diagnosis
 
Neural networks are parallel computing devices.docx.pdf
Neural networks are parallel computing devices.docx.pdfNeural networks are parallel computing devices.docx.pdf
Neural networks are parallel computing devices.docx.pdf
 
Neural Network
Neural NetworkNeural Network
Neural Network
 
Neural network
Neural networkNeural network
Neural network
 
Neuralnetwork 101222074552-phpapp02
Neuralnetwork 101222074552-phpapp02Neuralnetwork 101222074552-phpapp02
Neuralnetwork 101222074552-phpapp02
 
Neural networks of artificial intelligence
Neural networks of artificial  intelligenceNeural networks of artificial  intelligence
Neural networks of artificial intelligence
 
02 Fundamental Concepts of ANN
02 Fundamental Concepts of ANN02 Fundamental Concepts of ANN
02 Fundamental Concepts of ANN
 
Soft Computing-173101
Soft Computing-173101Soft Computing-173101
Soft Computing-173101
 
Introduction to Artificial Neural Networks
Introduction to Artificial Neural Networks Introduction to Artificial Neural Networks
Introduction to Artificial Neural Networks
 
Artificial Neural Network report
Artificial Neural Network reportArtificial Neural Network report
Artificial Neural Network report
 
Neural network and fuzzy logic
Neural network and fuzzy logicNeural network and fuzzy logic
Neural network and fuzzy logic
 
Lesson 37
Lesson 37Lesson 37
Lesson 37
 
AI Lesson 37
AI Lesson 37AI Lesson 37
AI Lesson 37
 
MaLAI_Hyderabad presentation
MaLAI_Hyderabad presentationMaLAI_Hyderabad presentation
MaLAI_Hyderabad presentation
 
neural networks
 neural networks neural networks
neural networks
 
Artificial Neural Network seminar presentation using ppt.
Artificial Neural Network seminar presentation using ppt.Artificial Neural Network seminar presentation using ppt.
Artificial Neural Network seminar presentation using ppt.
 
ANN.pptx
ANN.pptxANN.pptx
ANN.pptx
 
Neural net NWU 4.3 Graphics Course
Neural net NWU 4.3 Graphics CourseNeural net NWU 4.3 Graphics Course
Neural net NWU 4.3 Graphics Course
 
SujanKhamrui_28100119050.pptx
SujanKhamrui_28100119050.pptxSujanKhamrui_28100119050.pptx
SujanKhamrui_28100119050.pptx
 
SoftComputing5
SoftComputing5SoftComputing5
SoftComputing5
 

Último

"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr BaganFwdays
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfAlex Barbosa Coqueiro
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Enterprise Knowledge
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsMemoori
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebUiPathCommunity
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024Stephanie Beckett
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubKalema Edgar
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr LapshynFwdays
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brandgvaughan
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsSergiu Bodiu
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticscarlostorres15106
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsMiki Katsuragi
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsRizwan Syed
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024BookNet Canada
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxhariprasad279825
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Commit University
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfAddepto
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...Fwdays
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyAlfredo García Lavilla
 

Último (20)

"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan"ML in Production",Oleksandr Bagan
"ML in Production",Oleksandr Bagan
 
Unraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdfUnraveling Multimodality with Large Language Models.pdf
Unraveling Multimodality with Large Language Models.pdf
 
Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024Designing IA for AI - Information Architecture Conference 2024
Designing IA for AI - Information Architecture Conference 2024
 
AI as an Interface for Commercial Buildings
AI as an Interface for Commercial BuildingsAI as an Interface for Commercial Buildings
AI as an Interface for Commercial Buildings
 
Dev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio WebDev Dives: Streamline document processing with UiPath Studio Web
Dev Dives: Streamline document processing with UiPath Studio Web
 
What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024What's New in Teams Calling, Meetings and Devices March 2024
What's New in Teams Calling, Meetings and Devices March 2024
 
Unleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding ClubUnleash Your Potential - Namagunga Girls Coding Club
Unleash Your Potential - Namagunga Girls Coding Club
 
DMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special EditionDMCC Future of Trade Web3 - Special Edition
DMCC Future of Trade Web3 - Special Edition
 
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
"Federated learning: out of reach no matter how close",Oleksandr Lapshyn
 
WordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your BrandWordPress Websites for Engineers: Elevate Your Brand
WordPress Websites for Engineers: Elevate Your Brand
 
DevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platformsDevEX - reference for building teams, processes, and platforms
DevEX - reference for building teams, processes, and platforms
 
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmaticsKotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
Kotlin Multiplatform & Compose Multiplatform - Starter kit for pragmatics
 
Vertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering TipsVertex AI Gemini Prompt Engineering Tips
Vertex AI Gemini Prompt Engineering Tips
 
Scanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL CertsScanning the Internet for External Cloud Exposures via SSL Certs
Scanning the Internet for External Cloud Exposures via SSL Certs
 
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
New from BookNet Canada for 2024: BNC CataList - Tech Forum 2024
 
Artificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptxArtificial intelligence in cctv survelliance.pptx
Artificial intelligence in cctv survelliance.pptx
 
Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!Nell’iperspazio con Rocket: il Framework Web di Rust!
Nell’iperspazio con Rocket: il Framework Web di Rust!
 
Gen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdfGen AI in Business - Global Trends Report 2024.pdf
Gen AI in Business - Global Trends Report 2024.pdf
 
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks..."LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
"LLMs for Python Engineers: Advanced Data Analysis and Semantic Kernel",Oleks...
 
Commit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easyCommit 2024 - Secret Management made easy
Commit 2024 - Secret Management made easy
 

Introduction to Neural Networks in 40 Characters

  • 1. UNIT I  Introduction To Neural Networks  Biological Neural Networks  Characteristics of Neural Networks  Models of Neurons
  • 2. What is Neural Network?  An Artificial Neural Network (ANN) is an information processing paradigm that is inspired by the way biological nervous systems, such as the brain, to process information.  An artificial neural network is a system based on the operation of biological neural networks, in other words, is an emulation of biological neural system.
  • 3. Why learn Neural Networks?  Neural networks, with their remarkable ability to derive meaning from complicated or imprecise data, can be used to extract patterns and detect trends that are too complex to be noticed by either humans or other computer techniques.  A trained neural network can be thought of as an "expert" in the category of information it has been given to analyze.
  • 4. Advantages  Adaptive learning: An ability to learn how to do tasks based on the data given for training or initial experience.  Self-Organization: An ANN can create its own organization or representation of the information it receives during learning time.  Real Time Operation: ANN computations may be carried out in parallel, and special hardware devices are being designed and manufactured which take advantage of this capability.  Fault Tolerance via Redundant Information Coding: Partial destruction of a network leads to the corresponding degradation of performance. However, some network capabilities may be retained even with major network damage.
  • 5. Neural networks versus conventional computers  Conventional computers use an algorithmic approach i.e. the computer follows a set of instructions in order to solve a problem.  Neural networks process information in a similar way the human brain does. The network is composed of a large number of highly interconnected processing elements (neurons) working in parallel to solve a specific problem. Neural networks learn by example. They cannot be programmed to perform a specific task.  Neural networks and conventional algorithmic computers are not in competition but complement each other.
  • 6. Biological Neural Networks  A neural network is mans crude way of trying to simulate the brain electronically. So to understand how a neural net works we first must have a look at how the human brain works.
  • 7. Neuron  The human brain contains about 10 billion nerve cells, or neurons.  Each neuron is connected to thousands of other neurons and communicates with them via electrochemical signals.   Signals coming into the neuron are received via junctions called synapses, these in turn are located at the end of branches of the neuron cell called dendrites.
  • 8.
  • 9.
  • 10. Characteristics of Neural Network  parallel, distributed information processing  high degree of connectivity among basic units  connections are modifiable based on experience  learning is a constant process, and usually unsupervised  learning is based only on local information  performance degrades gracefully if some units are removed
  • 11. Summary  Neural Networks exhibits brain like behaviors like:  Learning  Association  Categorization  Generalization  Feature Extraction  Optimization  Noise Immunity
  • 12. Models of Neuron  An artificial neuron is simply an electronically modeled biological neuron. How many neurons are used depends on the task at hand.
  • 14. McCulloch Pitts Model  The early model of an artificial neuron is introduced by Warren McCulloch a neuroscientist and Walter Pitts a logician in 1943.  The McCulloch-Pitts neural model is also known as linear threshold gate.
  • 15. An Example Object Purple? Round? Eat? Blueberry 1 1 1 Golf Ball 0 1 0 Banana 0 0 0
  • 16.
  • 17. Problems  Set the threshold so that the bird eats any object that is round or purple or both.  Set the threshold so that the bird eats all the objects.
  • 18. Excitatory & Inhibitory  The signals are called excitatory because they excite the neuron toward possibly sending its own signal.  So as the neuron receives more and more excitatory signals, it gets more and more excited, until the threshold is reached, and the neuron sends out its own signal.
  • 19. The Inhibitory signals have the effect of inhibiting the neuron from sending a signal.  When a neuron receives an inhibitory signal, it becomes less excited, and so it takes more excitatory signals to reach the neuron's threshold.  In effect, inhibitory signals subtract from the total of the excitatory signals, making the neuron more relaxed, and moving the neuron away from its threshold.
  • 20. Perceptron  A perceptron which was introduced by Frank Rosenblatt in 1958.  Essentially the perceptron is an MCP neuron where the inputs are first passed through some "preprocessors" which are called association units.  These association units detect the presence of certain specific features in the inputs.
  • 21. Perceptron  In essence an association unit is also an MCP neuron which is 1 if a single specific pattern of inputs is received, and it is 0 for all other possible patterns of inputs.
  • 22. Adaline (Adaptive linear element)  An important generalization of the perceptron training algorithm.  It was presented by Widrow and Hoff as the 'least mean square' (LMS) learning procedure, also known as the delta rule.  The main functional difference with the Perceptron training rule is the way the output of the system is used in the learning rule.
  • 23. Neural Network Topologies  The arrangements of the processing units, connections, and pattern input / output is referred to as topology.  Connections can be made in two ways Interlayer Intralayer
  • 24. Feedforward & Feedback  Feed-forward ANNs allow signals to travel one way only; from input to output.  There is no feedback (loops) i.e. the output of any layer does not affect that same layer.  They are extensively used in pattern recognition. This type of organization is also referred to as bottom-up or top-down.
  • 26. Basic Learning Rules  Learning: The ability of the neural network (NN) to learn from its environment and to improve its performance through learning.  Learning is a process by which the free parameters of a neural network are adapted through a process of stimulation by the environment in which the network is embedded.  The type of the learning is determined by the manner in which the parameter changes take place.
  • 27. Learning Rules  Hebb’s Law  Perceptron Learning Law  Delta Learning Law  Widrow and Hoff LMS Learning Law  Correlation Learning Law  Instar ( Winner – take – all)  Outstar Learning Law
  • 28. Supervised Learning  During the training session of neural network, an input stimulus is applied that results in output response.  This response is compared with an priori desired output signal, the target response.  If the actual response differs from the target response, the neural network generates an error signal.
  • 29. This error signal is used to calculate the adjustments that should be made to network’s synaptic weights so that the actual o/p matches the target output.  This error minimization process requires a special circuit known as supervisor or teacher, hence the name Supervised learning.  A neural net is said to learn supervised, if the desired output is already known.
  • 30. Unsupervised Learning  Unsupervised learning does not require a teacher; that is there is no target output.  During the training session, the neural net receives at its input many different excitations or input patterns.  The neural net arbitrarily organizes the patterns into categories.
  • 31. When the stimulus is applied later, the neural net provides an output response indicating the class to which the stimulus belongs.  If a class cannot be found for the input stimulus, a new class is generated.  Even though unsupervised learning does not require a teacher, it requires guidelines to determine how it will form groups.
  • 32. Reinforced Learning  Reinforced learning requires one or more neurons at the output layer and a teacher.  Unlike supervised learning, teacher does not indicate how close the actual output is to the target output but whether the actual output is the same with target output or not.  The teacher does not present the target output to the network, but presents only a pass/fail indication.
  • 33. Contd..  The error signal generated during the training session is binary: pass or fail.  If the teachers indication is bad, the network readjusts its parameters and tries again and again until it gets its output response right.  There is no clear indication if the output response is moving in the right direction or how close it is to the correct response it is.
  • 34. Competitive Learning  It is another form of supervised learning that is distinctive because of its characteristics operation and architecture.  Several neurons are at the output layer. When an input stimulus is applied, each output neuron competes with the others to produce the closest output signal to the target.
  • 35. Contd..  This output becomes the dominant one, and the other outputs cease producing an output signal for that stimulus.  For another stimulus, another output neuron becomes the dominant one.  Thus each output neuron is trained to respond to a different input stimulus.