Artificial neural networks and its applications

What You Will Learn
From This
Presentation:
 What is Neural Network?
 What is Artificial Network Network?
 What id Difference Between AAN and BNN?
 How Does ANN Work?
 How is the AAN Architecture?
 What Are Types Of AAN?
 What Are The Applications of AAN?
What Is Neural Network?
 NeuralNeuron
 Basic Functional Unit
What Is Neural
Network?(Contd.)
 Parts Of Neuron:
 Dendrite-receive signal from neurons
 Soma-sums up incoming signals
 Axon-fires signal down the neurons
 Synapse-interconnection-one neuron to other
What is Artificial Neural
Network?
 Biologically inspired Simulations
 Used for:
 Clustering
 Classification
 Pattern Recognition
Difference Between AAN
and BNN
Parameters BNN ANN
Speed Fast
NanoSecond
s
Slow
Milliseconds
Processing Serial Parallel
Size And
Complexity
Less Size
And
Complexity
More Size
And
Complexity
Storage Replacable Complexe
Interconnec
How Is ANN Developed?
 Parallel Processing
 Learn By Pattern
 Essence Program
 Use of application-specific multi-chips.
Layers Of ANN
 Input Layer-receive input-outside world
 Output Layer-respond to information-how it learned a
task
 Hidden layer-main layer-all processing-transform input-
output
How Is ANN
Developed?(Contd.)
 Activation function-transfer function-output
 Activation:
 Linear
 Non-Linear
How Does ANN Actually
Work?
 Large unit work-process information
 Weighted Directed Graph
 Nodes,directed edges with weights
 Information-external world
 Input Multiplied By Corresponding weights
 Weight input-sum=1
 If(sum!=1),basied added
How Does ANN Actually
Work?(Contd.)
 Adjusting weights and bias
 Neural Network-trained first
 Training-defined set of rules-learning algorithm
Neural Network
Architecture
 Perceptron Model in Neural Networks
 Radial Basis Function Neural Network
 Multilayer Perceptron Neural Network
 Recurrent Neural Network
 Long Short-Term Memory Neural Network (LSTM)
 Hopfield Network
 Convolutional Neural Network
 Modular Neural Network
 Physical Neural Network
Types Of Neural Network
Parameters Types
Based On
Connection
Pattern
Feed Forward
Recurrent
Based On
No.of Hidden
Layer
Single Layer
Multilayer
Based on
Nature of
Weight
Fixed
Adaptive
What Are Types Of ANN?
 Classification Neural Network
 Prediction Neural Network
 Clustering Neural Network
 Association Neural Network
Application Of ANN
 Process modeling and control
 Machine Diagnostics
 Portfolio Management
 Target Recognition
 Medical Diagnosis
 Credit Rating
 Targeted Marketing
 Voice recognition
 Face recognition
 Financial Forecasting
 Intelligent searching
 Fraud detection
Advantages Of ANN
 Perform tasks-linear function/program cannot
 Continue parallel processing-even if somethings fail
 Implementated-any application
 Doesnot need to be reprogrammed
Limitations of ANN
 Needs training to be performed
 Needs to be emulated
 Require-high processing time
Conclusion:
 ANN-very benefial
 Very efficient-neural building-image recogntion
 Requires efficient computing machines
At the end of this PPT ,we
haved learned:
 What is ANN?
 How is it Developed?
 What are its Types?
 What its Apllications?
Questions
THANKYOU
1 von 20

Más contenido relacionado

Was ist angesagt?(20)

Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
Manasa Mona1.7K views
Artificial Neural Networks - ANNArtificial Neural Networks - ANN
Artificial Neural Networks - ANN
Mohamed Talaat10.4K views
Neural network & its applications Neural network & its applications
Neural network & its applications
Ahmed_hashmi195.2K views
Deep learningDeep learning
Deep learning
Ratnakar Pandey11.4K views
Reinforcement learning Reinforcement learning
Reinforcement learning
Chandra Meena44.4K views
Artificial neural networksArtificial neural networks
Artificial neural networks
madhu sudhakar502 views
Artificial Neural NetworksArtificial Neural Networks
Artificial Neural Networks
Arslan Zulfiqar369 views
neural networkneural network
neural network
STUDENT115.8K views
Convolution Neural Network (CNN)Convolution Neural Network (CNN)
Convolution Neural Network (CNN)
Suraj Aavula13.4K views
Artificial neural networkArtificial neural network
Artificial neural network
Mohd Arafat Shaikh23K views
Neural networkNeural network
Neural network
Silicon15.9K views
Artificial Neural Network in Medical DiagnosisArtificial Neural Network in Medical Diagnosis
Artificial Neural Network in Medical Diagnosis
Adityendra Kumar Singh735 views
Deep learningDeep learning
Deep learning
Benha University8.4K views
Nural network ER. Abhishek  k. upadhyayNural network ER. Abhishek  k. upadhyay
Nural network ER. Abhishek k. upadhyay
abhishek upadhyay868 views
Intro to Neural NetworksIntro to Neural Networks
Intro to Neural Networks
Dean Wyatte1.6K views

Similar a Artificial neural networks and its applications

Neural network Neural network
Neural network Faireen
575 views20 Folien
Neural networkNeural network
Neural networkSaddam Hussain
771 views17 Folien

Similar a Artificial neural networks and its applications (20)

Neural network Neural network
Neural network
Faireen575 views
Deep learning notes.pptxDeep learning notes.pptx
Deep learning notes.pptx
Pandi Gingee17 views
Artificial Neural networksArtificial Neural networks
Artificial Neural networks
Learnbay Datascience25 views
Neural networkNeural network
Neural network
Saddam Hussain771 views
Neural networksNeural networks
Neural networks
Learnbay Datascience333 views
Neural networksNeural networks
Neural networks
Rizwan Rizzu2.2K views
Quantum neural networkQuantum neural network
Quantum neural network
surat murthy576 views
Ann model and its applicationAnn model and its application
Ann model and its application
milan107468 views
Neural NetworksNeural Networks
Neural Networks
NikitaRuhela15.2K views
deeplearningdeeplearning
deeplearning
huda2018109 views
Nn devsNn devs
Nn devs
EasyMedico.com450 views
ANN.ppt[1].pptxANN.ppt[1].pptx
ANN.ppt[1].pptx
SrujanaChiliveri2 views
NeuralNeural
Neural
Archit Rastogi3.3K views

Último(20)

Artificial neural networks and its applications

  • 1. What You Will Learn From This Presentation:  What is Neural Network?  What is Artificial Network Network?  What id Difference Between AAN and BNN?  How Does ANN Work?  How is the AAN Architecture?  What Are Types Of AAN?  What Are The Applications of AAN?
  • 2. What Is Neural Network?  NeuralNeuron  Basic Functional Unit
  • 3. What Is Neural Network?(Contd.)  Parts Of Neuron:  Dendrite-receive signal from neurons  Soma-sums up incoming signals  Axon-fires signal down the neurons  Synapse-interconnection-one neuron to other
  • 4. What is Artificial Neural Network?  Biologically inspired Simulations  Used for:  Clustering  Classification  Pattern Recognition
  • 5. Difference Between AAN and BNN Parameters BNN ANN Speed Fast NanoSecond s Slow Milliseconds Processing Serial Parallel Size And Complexity Less Size And Complexity More Size And Complexity Storage Replacable Complexe Interconnec
  • 6. How Is ANN Developed?  Parallel Processing  Learn By Pattern  Essence Program  Use of application-specific multi-chips.
  • 7. Layers Of ANN  Input Layer-receive input-outside world  Output Layer-respond to information-how it learned a task  Hidden layer-main layer-all processing-transform input- output
  • 8. How Is ANN Developed?(Contd.)  Activation function-transfer function-output  Activation:  Linear  Non-Linear
  • 9. How Does ANN Actually Work?  Large unit work-process information  Weighted Directed Graph  Nodes,directed edges with weights  Information-external world  Input Multiplied By Corresponding weights  Weight input-sum=1  If(sum!=1),basied added
  • 10. How Does ANN Actually Work?(Contd.)  Adjusting weights and bias  Neural Network-trained first  Training-defined set of rules-learning algorithm
  • 11. Neural Network Architecture  Perceptron Model in Neural Networks  Radial Basis Function Neural Network  Multilayer Perceptron Neural Network  Recurrent Neural Network  Long Short-Term Memory Neural Network (LSTM)  Hopfield Network  Convolutional Neural Network  Modular Neural Network  Physical Neural Network
  • 12. Types Of Neural Network Parameters Types Based On Connection Pattern Feed Forward Recurrent Based On No.of Hidden Layer Single Layer Multilayer Based on Nature of Weight Fixed Adaptive
  • 13. What Are Types Of ANN?  Classification Neural Network  Prediction Neural Network  Clustering Neural Network  Association Neural Network
  • 14. Application Of ANN  Process modeling and control  Machine Diagnostics  Portfolio Management  Target Recognition  Medical Diagnosis  Credit Rating  Targeted Marketing  Voice recognition  Face recognition  Financial Forecasting  Intelligent searching  Fraud detection
  • 15. Advantages Of ANN  Perform tasks-linear function/program cannot  Continue parallel processing-even if somethings fail  Implementated-any application  Doesnot need to be reprogrammed
  • 16. Limitations of ANN  Needs training to be performed  Needs to be emulated  Require-high processing time
  • 17. Conclusion:  ANN-very benefial  Very efficient-neural building-image recogntion  Requires efficient computing machines
  • 18. At the end of this PPT ,we haved learned:  What is ANN?  How is it Developed?  What are its Types?  What its Apllications?