Neural Networks in Data Mining - “An Overview”

Dr.(Mrs).Gethsiyal Augasta
Dr.(Mrs).Gethsiyal AugastaAsst. Professor, CS Dept, Kamaraj College um Kamaraj College, Tiruchendur Road, Tuticorin - 628 003.
Neural Networks
in Data Mining -
“An Overview”
Agenda
u Introduction
u Data Mining Techniques
u Neural Networks for Data Mining?
 Neural Networks Classification
 Neural Networks Pruning
 Neural Networks Rule Extraction
u Conclusion
u Questions?
 Extraction of interesting (non-trivial,
implicit, previously unknown and
potentially useful) information or patterns
from data in large databases
 It is an essential step in the process of
knowledge discovery.
Data Mining
• data cleaning
• data integration
• data selection
• data transformation
• data mining
• pattern evaluation
• knowledge presentation.
Steps of Knowledge Discovery
Data Mining: A KDD Process
 Data mining—core of
knowledge discovery
process
Data Cleaning
Data Integration
Databases
Data Warehouse
Task-relevant Data
Selection
Data Mining
Pattern Evaluation
Why Data mining?
Data explosion problem
Automated data collection tools and
mature database technology lead to
tremendous amounts of data stored in
databases, data warehouses and other
information repositories
We are drowning in data, but starving for
knowledge!
Solution: Data warehousing and data mining
Tasks of data mining
 Concept Description
 Association
 Classification
 Prediction
 Cluster Analysis
 Outlier Analysis
Classification
It is the process of finding a model
that is able to predict the class of
objects whose label is unknown.
For eg. It can classify the customers who can pay the
loan based on the existing records in the bank database.
 Decision trees
 Bayesian classification
 Neural networks
 Genetic algorithms
 Memory Based Reasoning
etc.,
Classification methods
 high tolerance of noisy data.
 ability to classify patterns on which they
have not been trained.
 can be used when there is little
knowledge of the relationships between
attribute and classes.
Why Neural networks?
 well suited for continuous valued inputs
and outputs unlike most decision tree
algorithms.
 rules can be extracted easily by available
techniques from trained neural network.
Why Neural networks?
- Contd.
Neural Networks
It is the study of how to make
computers to make sensible
decisions and to learn by ordinary
experience as we do.
Neurons
The human brain consists has about 100 billion neurons and
100 trillion connections (synapses) between them.
Here is what a typical neuron looks like:
Many highly specialized types of neurons exist, and these
differ widely in appearance. Characteristically, neurons are
highly asymmetric in shape.
 It consists of an input layer, one or more
hidden layers and an output layer.
Input Layer
Hidden Layer
Output Layer
Structure of Multi layer feed forward neural network
Multi layer feed forward neural network
Backpropagation
 Backpropagation is the neural network
learning algorithm.
 It learns by iteratively processing a
dataset of training examples, comparing the
network's prediction for each example with
the actual known target value.
Overview of BP
The backpropagation algorithm learns
the network by iteratively processing the
np training examples of a dataset,
comparing the networks result ok for
each example with the desired known
target value dk for each target class k in
a dataset.
Consider a fully connected three layer
feedforward neural network as in figure ,
X1
X2
Xi
Xl
…
…
…
h1
O1
…
w11
w12
wl1
wlm
hm
On
v11
v12
vm1
vmn
Overviewof BP – Contd.
Bias (-1)
Bias (-1)
h2
Consists of l input neurons, m hidden
neurons and n output neurons
np be the number of examples consider
for training.
 Let xip be the ith input unit of pth
example in a dataset, where i= 1, 2,… l.
Wij be the weight between input unit
neuron i to hidden unit neuron j, where
j=1,2…m,
Overview of BP – Contd.
vjk be the weight between hidden neuron
j to output neuron k, where k=1, 2,… n.
initially the weights wij and vjk takes the
random value between -1 to 1.
Let hj be the activation value of the
hidden neuron j
ok be the actual output of the kth neuron.
Overview of BP – Contd.
Bias
• It is a threshold value that serves to
vary the activity of the neuron.
• The bias input is fixed and always
equals -1.
Overview of BP – Contd.
The activation value of hidden neuron
hj for pth examples can be calculated by,
Overview of BP – Contd.
The actual output ok can be calculated
by,
Overview of SBP – Contd.
 Weights are modified for each example
so as to minimize the mean squared
error (mse).
 The value of mse can be calculated
according to the following equation
Overview of BP – Contd.
Weight updation are made in the
backward direction i.e., from the
output layer through hidden layer
and to input layer.
Overview of BP – Contd.
Learning Rate λ
 avoids local minimum (where the
weights appear to converge but are not
at the optimal solution).
encourages finding global minimum.
Typically having a value between 0.0 to
1.0.
Overview of BP – Contd.
For each unit k in the output layer
 compute the Error using
Errk = ok(1-ok)(dk-ok)
For each weight vjk in network
 compute weight increment using
Δvjk=(λ) Errk*hj
 update the weight vjk using
vjk = vjk + Δvjk
Overview of BP – Contd.
For each unit j in the hidden layers, from
the last to the first hidden layer
compute the Error using
Errj = hj (1-hj) Σ Errk*vjk;
For each weight wij in network
 compute weight increment using
Δwij=(λ)*Errj*xip
 update the weight wij using
wij = wij + Δwij
Overview of BP – Contd.
Overview of BP – Contd.
For each bias Ǿj in network
 compute the bias increment
using
Δ Ǿj = (λ)*Errj
 update the bias weight using
Ǿj = Ǿj + Δ Ǿj
The algorithm stops the learning when,
• The mean squared error is below a
threshold value.
• A pre specified number of epochs has
expired
Overview of BP – Contd.
Random data selection method
 The training and testing examples are
taken randomly from each class.
K-fold cross validation method
Example
The iris dataset is having 3 classes with
50 examples for each class. From each
class 25 examples are taken randomly for
training and another 25 examples are
taken randomly for testing the network.
Data selection method.
Performance Measures
Accuracy
It is the percentage of test dataset
that are correctly classified by the
classifier.
Speed
It refers to computational time and
cost involved in generating and using
given classifier.
Evolving Network Architectures
The success of ANNs largely depends on their
architecture.
 Small networks require long training time and can
be easily get trapped into a Local Minima.
 Large networks able to learn fast and avoids local
minima but with poor generalization.
 Optimal architecture is a network that is large
enough to learn the problem and is small enough
to generalize well.
approaches for optimizing Neural
Networks
Constructive methods
- new hidden units are added during the training
process, also called as Growing methods.
Destructive methods
- a large network is trained and then unimportant
nodes or weights are removed, also called as Pruning
methods.
Hybrid methods
- can both add and remove.
Pruning is defined as a network trimming within the
assumed initial architecture.
This can be accomplished by estimating the sensitivity
of the total error to the exclusion of each weight or
neuron in the network.
The weights or neurons which are insensitive to error
changes can be discarded after each step of training.
The trimmed network is of smaller size and is likely
give higher accuracy than before its trimming.
What is Pruning ?
Hepatitis Pruning Results
Step Current
Architecture
Acctest % Epochs Pruned Neurons
1 19-25-2 78.2 200 18 hidden neurons
2 19-7-2 80.5 50 5 hidden neurons
3 19-2-2 83.95 50 Pruning stops
Original network with architecture 19-25-2 with accuracy
78.2% is reduced to the architecture 19-2-2.
 Requires 0.76 seconds to obtain the pruned network.
Rule Extraction
Why Rule extraction?
An important drawback of neural networks is their lack of
explanation capability i.e., it is very difficult to understand how
an ANN has solved a problem. To overcome this problem
various rule extraction algorithms have been developed.
Rule extraction : It changes a black box system into a white
box system by translating the internal knowledge of a neural
network into a set of symbolic rules .
The classification process of a neural networks can be
described by a set of simple rules.
Extracted Rules of 6 real datasets.
•robots that can see, feel, and predict the world around them
•improved stock prediction
•common usage of self-driving cars
•composition of music
•handwritten documents to be automatically transformed into
formatted word processing documents
•trends found in the human genome to aid in the
understanding of the data compiled by the Human Genome
Project
•self-diagnosis of medical problems using neural networks
and much more!
NNs might, in the future, allow:
Neural Networks  in Data Mining -   “An Overview”
QUESTIONS
1 von 40

Recomendados

Machine Learning: Introduction to Neural Networks von
Machine Learning: Introduction to Neural NetworksMachine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural NetworksFrancesco Collova'
16.1K views42 Folien
Introduction to artificial neural network von
Introduction to artificial neural networkIntroduction to artificial neural network
Introduction to artificial neural networkDr. C.V. Suresh Babu
787 views39 Folien
Neural network von
Neural networkNeural network
Neural networkKRISH na TimeTraveller
9.1K views23 Folien
Decision tree induction \ Decision Tree Algorithm with Example| Data science von
Decision tree induction \ Decision Tree Algorithm with Example| Data scienceDecision tree induction \ Decision Tree Algorithm with Example| Data science
Decision tree induction \ Decision Tree Algorithm with Example| Data scienceMaryamRehman6
1.4K views30 Folien
Cluster analysis von
Cluster analysisCluster analysis
Cluster analysisKamalakshi Deshmukh-Samag
910 views17 Folien
04 Multi-layer Feedforward Networks von
04 Multi-layer Feedforward Networks04 Multi-layer Feedforward Networks
04 Multi-layer Feedforward NetworksTamer Ahmed Farrag, PhD
3.5K views27 Folien

Más contenido relacionado

Was ist angesagt?

Unsupervised learning clustering von
Unsupervised learning clusteringUnsupervised learning clustering
Unsupervised learning clusteringArshad Farhad
1K views23 Folien
Neural Networks: Least Mean Square (LSM) Algorithm von
Neural Networks: Least Mean Square (LSM) AlgorithmNeural Networks: Least Mean Square (LSM) Algorithm
Neural Networks: Least Mean Square (LSM) AlgorithmMostafa G. M. Mostafa
14.3K views34 Folien
Convolutional neural network from VGG to DenseNet von
Convolutional neural network from VGG to DenseNetConvolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNetSungminYou
998 views24 Folien
Artificial Neural Network von
Artificial Neural NetworkArtificial Neural Network
Artificial Neural NetworkAtul Krishna
1.3K views79 Folien
Fuzzy Clustering(C-means, K-means) von
Fuzzy Clustering(C-means, K-means)Fuzzy Clustering(C-means, K-means)
Fuzzy Clustering(C-means, K-means)Fellowship at Vodafone FutureLab
5.7K views24 Folien

Was ist angesagt?(20)

Unsupervised learning clustering von Arshad Farhad
Unsupervised learning clusteringUnsupervised learning clustering
Unsupervised learning clustering
Arshad Farhad1K views
Convolutional neural network from VGG to DenseNet von SungminYou
Convolutional neural network from VGG to DenseNetConvolutional neural network from VGG to DenseNet
Convolutional neural network from VGG to DenseNet
SungminYou998 views
Artificial Neural Network von Atul Krishna
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
Atul Krishna1.3K views
07 regularization von Ronald Teo
07 regularization07 regularization
07 regularization
Ronald Teo851 views
Introduction to CNN von Shuai Zhang
Introduction to CNNIntroduction to CNN
Introduction to CNN
Shuai Zhang8.9K views
Introduction to Recurrent Neural Network von Knoldus Inc.
Introduction to Recurrent Neural NetworkIntroduction to Recurrent Neural Network
Introduction to Recurrent Neural Network
Knoldus Inc.2K views
Feed forward ,back propagation,gradient descent von Muhammad Rasel
Feed forward ,back propagation,gradient descentFeed forward ,back propagation,gradient descent
Feed forward ,back propagation,gradient descent
Muhammad Rasel612 views
Convolutional Neural Networks von Ashray Bhandare
Convolutional Neural NetworksConvolutional Neural Networks
Convolutional Neural Networks
Ashray Bhandare16.2K views
Classification Based Machine Learning Algorithms von Md. Main Uddin Rony
Classification Based Machine Learning AlgorithmsClassification Based Machine Learning Algorithms
Classification Based Machine Learning Algorithms
Md. Main Uddin Rony9.9K views
Back propagation von Nagarajan
Back propagationBack propagation
Back propagation
Nagarajan66.7K views
Deep Learning With Neural Networks von Aniket Maurya
Deep Learning With Neural NetworksDeep Learning With Neural Networks
Deep Learning With Neural Networks
Aniket Maurya3.1K views
MACHINE LEARNING - GENETIC ALGORITHM von Puneet Kulyana
MACHINE LEARNING - GENETIC ALGORITHMMACHINE LEARNING - GENETIC ALGORITHM
MACHINE LEARNING - GENETIC ALGORITHM
Puneet Kulyana5.1K views

Similar a Neural Networks in Data Mining - “An Overview”

08 neural networks von
08 neural networks08 neural networks
08 neural networksankit_ppt
577 views75 Folien
2. NEURAL NETWORKS USING GENETIC ALGORITHMS.pptx von
2. NEURAL NETWORKS USING GENETIC ALGORITHMS.pptx2. NEURAL NETWORKS USING GENETIC ALGORITHMS.pptx
2. NEURAL NETWORKS USING GENETIC ALGORITHMS.pptxssuser67281d
37 views19 Folien
Artificial Neural networks von
Artificial Neural networksArtificial Neural networks
Artificial Neural networksLearnbay Datascience
25 views29 Folien
AI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies von
AI Class Topic 6: Easy Way to Learn Deep Learning AI TechnologiesAI Class Topic 6: Easy Way to Learn Deep Learning AI Technologies
AI Class Topic 6: Easy Way to Learn Deep Learning AI TechnologiesValue Amplify Consulting
107 views61 Folien
Deep learning from a novice perspective von
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspectiveAnirban Santara
1.2K views25 Folien
Introduction Of Artificial neural network von
Introduction Of Artificial neural networkIntroduction Of Artificial neural network
Introduction Of Artificial neural networkNagarajan
18.4K views93 Folien

Similar a Neural Networks in Data Mining - “An Overview”(20)

08 neural networks von ankit_ppt
08 neural networks08 neural networks
08 neural networks
ankit_ppt577 views
2. NEURAL NETWORKS USING GENETIC ALGORITHMS.pptx von ssuser67281d
2. NEURAL NETWORKS USING GENETIC ALGORITHMS.pptx2. NEURAL NETWORKS USING GENETIC ALGORITHMS.pptx
2. NEURAL NETWORKS USING GENETIC ALGORITHMS.pptx
ssuser67281d37 views
Deep learning from a novice perspective von Anirban Santara
Deep learning from a novice perspectiveDeep learning from a novice perspective
Deep learning from a novice perspective
Anirban Santara1.2K views
Introduction Of Artificial neural network von Nagarajan
Introduction Of Artificial neural networkIntroduction Of Artificial neural network
Introduction Of Artificial neural network
Nagarajan18.4K views
Handwritten Digit Recognition using Convolutional Neural Networks von IRJET Journal
Handwritten Digit Recognition using Convolutional Neural  NetworksHandwritten Digit Recognition using Convolutional Neural  Networks
Handwritten Digit Recognition using Convolutional Neural Networks
IRJET Journal523 views
Autoencoders for image_classification von Cenk Bircanoğlu
Autoencoders for image_classificationAutoencoders for image_classification
Autoencoders for image_classification
Cenk Bircanoğlu4.9K views
Hand Written Digit Classification von ijtsrd
Hand Written Digit ClassificationHand Written Digit Classification
Hand Written Digit Classification
ijtsrd139 views
Basics of Artificial Neural Network von Subham Preetam
Basics of Artificial Neural Network Basics of Artificial Neural Network
Basics of Artificial Neural Network
Subham Preetam66 views
X-TREPAN: A MULTI CLASS REGRESSION AND ADAPTED EXTRACTION OF COMPREHENSIBLE D... von cscpconf
X-TREPAN: A MULTI CLASS REGRESSION AND ADAPTED EXTRACTION OF COMPREHENSIBLE D...X-TREPAN: A MULTI CLASS REGRESSION AND ADAPTED EXTRACTION OF COMPREHENSIBLE D...
X-TREPAN: A MULTI CLASS REGRESSION AND ADAPTED EXTRACTION OF COMPREHENSIBLE D...
cscpconf149 views
X-TREPAN : A Multi Class Regression and Adapted Extraction of Comprehensible ... von csandit
X-TREPAN : A Multi Class Regression and Adapted Extraction of Comprehensible ...X-TREPAN : A Multi Class Regression and Adapted Extraction of Comprehensible ...
X-TREPAN : A Multi Class Regression and Adapted Extraction of Comprehensible ...
csandit523 views
ML Module 3 Non Linear Learning.pptx von DebabrataPain1
ML Module 3 Non Linear Learning.pptxML Module 3 Non Linear Learning.pptx
ML Module 3 Non Linear Learning.pptx
DebabrataPain15 views
Deep Learning Interview Questions And Answers | AI & Deep Learning Interview ... von Simplilearn
Deep Learning Interview Questions And Answers | AI & Deep Learning Interview ...Deep Learning Interview Questions And Answers | AI & Deep Learning Interview ...
Deep Learning Interview Questions And Answers | AI & Deep Learning Interview ...
Simplilearn1.4K views
Artificial neural network for machine learning von grinu
Artificial neural network for machine learningArtificial neural network for machine learning
Artificial neural network for machine learning
grinu572 views
Artificial Neural Networks (ANNS) For Prediction of California Bearing Ratio ... von IJMER
Artificial Neural Networks (ANNS) For Prediction of California Bearing Ratio ...Artificial Neural Networks (ANNS) For Prediction of California Bearing Ratio ...
Artificial Neural Networks (ANNS) For Prediction of California Bearing Ratio ...
IJMER296 views
Applications of machine learning in Wireless sensor networks. von Sahana B S
Applications of machine learning in Wireless sensor networks.Applications of machine learning in Wireless sensor networks.
Applications of machine learning in Wireless sensor networks.
Sahana B S605 views

Último

[DSC Europe 23][AI:CSI] Dragan Pleskonjic - AI Impact on Cybersecurity and P... von
[DSC Europe 23][AI:CSI]  Dragan Pleskonjic - AI Impact on Cybersecurity and P...[DSC Europe 23][AI:CSI]  Dragan Pleskonjic - AI Impact on Cybersecurity and P...
[DSC Europe 23][AI:CSI] Dragan Pleskonjic - AI Impact on Cybersecurity and P...DataScienceConferenc1
8 views36 Folien
Employees attrition von
Employees attritionEmployees attrition
Employees attritionMaryAlejandraDiaz
5 views5 Folien
Data Journeys Hard Talk workshop final.pptx von
Data Journeys Hard Talk workshop final.pptxData Journeys Hard Talk workshop final.pptx
Data Journeys Hard Talk workshop final.pptxinfo828217
11 views18 Folien
apple.pptx von
apple.pptxapple.pptx
apple.pptxhoneybeeqwe
6 views15 Folien
PRIVACY AWRE PERSONAL DATA STORAGE von
PRIVACY AWRE PERSONAL DATA STORAGEPRIVACY AWRE PERSONAL DATA STORAGE
PRIVACY AWRE PERSONAL DATA STORAGEantony420421
7 views56 Folien
Best Home Security Systems.pptx von
Best Home Security Systems.pptxBest Home Security Systems.pptx
Best Home Security Systems.pptxmogalang
9 views16 Folien

Último(20)

[DSC Europe 23][AI:CSI] Dragan Pleskonjic - AI Impact on Cybersecurity and P... von DataScienceConferenc1
[DSC Europe 23][AI:CSI]  Dragan Pleskonjic - AI Impact on Cybersecurity and P...[DSC Europe 23][AI:CSI]  Dragan Pleskonjic - AI Impact on Cybersecurity and P...
[DSC Europe 23][AI:CSI] Dragan Pleskonjic - AI Impact on Cybersecurity and P...
Data Journeys Hard Talk workshop final.pptx von info828217
Data Journeys Hard Talk workshop final.pptxData Journeys Hard Talk workshop final.pptx
Data Journeys Hard Talk workshop final.pptx
info82821711 views
PRIVACY AWRE PERSONAL DATA STORAGE von antony420421
PRIVACY AWRE PERSONAL DATA STORAGEPRIVACY AWRE PERSONAL DATA STORAGE
PRIVACY AWRE PERSONAL DATA STORAGE
antony4204217 views
Best Home Security Systems.pptx von mogalang
Best Home Security Systems.pptxBest Home Security Systems.pptx
Best Home Security Systems.pptx
mogalang9 views
[DSC Europe 23][AI:CSI] Aleksa Stojanovic - Applying AI for Threat Detection ... von DataScienceConferenc1
[DSC Europe 23][AI:CSI] Aleksa Stojanovic - Applying AI for Threat Detection ...[DSC Europe 23][AI:CSI] Aleksa Stojanovic - Applying AI for Threat Detection ...
[DSC Europe 23][AI:CSI] Aleksa Stojanovic - Applying AI for Threat Detection ...
SUPER STORE SQL PROJECT.pptx von khan888620
SUPER STORE SQL PROJECT.pptxSUPER STORE SQL PROJECT.pptx
SUPER STORE SQL PROJECT.pptx
khan88862013 views
Dr. Ousmane Badiane-2023 ReSAKSS Conference von AKADEMIYA2063
Dr. Ousmane Badiane-2023 ReSAKSS ConferenceDr. Ousmane Badiane-2023 ReSAKSS Conference
Dr. Ousmane Badiane-2023 ReSAKSS Conference
AKADEMIYA20635 views
[DSC Europe 23] Luca Morena - From Psychohistory to Curious Machines von DataScienceConferenc1
[DSC Europe 23] Luca Morena - From Psychohistory to Curious Machines[DSC Europe 23] Luca Morena - From Psychohistory to Curious Machines
[DSC Europe 23] Luca Morena - From Psychohistory to Curious Machines
Games, Queries, and Argumentation Frameworks: Time for a Family Reunion von Bertram Ludäscher
Games, Queries, and Argumentation Frameworks: Time for a Family ReunionGames, Queries, and Argumentation Frameworks: Time for a Family Reunion
Games, Queries, and Argumentation Frameworks: Time for a Family Reunion
6498-Butun_Beyinli_Cocuq-Daniel_J.Siegel-Tina_Payne_Bryson-2011-259s.pdf von 10urkyr34
6498-Butun_Beyinli_Cocuq-Daniel_J.Siegel-Tina_Payne_Bryson-2011-259s.pdf6498-Butun_Beyinli_Cocuq-Daniel_J.Siegel-Tina_Payne_Bryson-2011-259s.pdf
6498-Butun_Beyinli_Cocuq-Daniel_J.Siegel-Tina_Payne_Bryson-2011-259s.pdf
10urkyr347 views
[DSC Europe 23] Danijela Horak - The Innovator’s Dilemma: to Build or Not to ... von DataScienceConferenc1
[DSC Europe 23] Danijela Horak - The Innovator’s Dilemma: to Build or Not to ...[DSC Europe 23] Danijela Horak - The Innovator’s Dilemma: to Build or Not to ...
[DSC Europe 23] Danijela Horak - The Innovator’s Dilemma: to Build or Not to ...
Shreyas hospital statistics.pdf von samithavinal
Shreyas hospital statistics.pdfShreyas hospital statistics.pdf
Shreyas hospital statistics.pdf
samithavinal5 views

Neural Networks in Data Mining - “An Overview”

  • 1. Neural Networks in Data Mining - “An Overview”
  • 2. Agenda u Introduction u Data Mining Techniques u Neural Networks for Data Mining?  Neural Networks Classification  Neural Networks Pruning  Neural Networks Rule Extraction u Conclusion u Questions?
  • 3.  Extraction of interesting (non-trivial, implicit, previously unknown and potentially useful) information or patterns from data in large databases  It is an essential step in the process of knowledge discovery. Data Mining
  • 4. • data cleaning • data integration • data selection • data transformation • data mining • pattern evaluation • knowledge presentation. Steps of Knowledge Discovery
  • 5. Data Mining: A KDD Process  Data mining—core of knowledge discovery process Data Cleaning Data Integration Databases Data Warehouse Task-relevant Data Selection Data Mining Pattern Evaluation
  • 6. Why Data mining? Data explosion problem Automated data collection tools and mature database technology lead to tremendous amounts of data stored in databases, data warehouses and other information repositories We are drowning in data, but starving for knowledge! Solution: Data warehousing and data mining
  • 7. Tasks of data mining  Concept Description  Association  Classification  Prediction  Cluster Analysis  Outlier Analysis
  • 8. Classification It is the process of finding a model that is able to predict the class of objects whose label is unknown. For eg. It can classify the customers who can pay the loan based on the existing records in the bank database.
  • 9.  Decision trees  Bayesian classification  Neural networks  Genetic algorithms  Memory Based Reasoning etc., Classification methods
  • 10.  high tolerance of noisy data.  ability to classify patterns on which they have not been trained.  can be used when there is little knowledge of the relationships between attribute and classes. Why Neural networks?
  • 11.  well suited for continuous valued inputs and outputs unlike most decision tree algorithms.  rules can be extracted easily by available techniques from trained neural network. Why Neural networks? - Contd.
  • 12. Neural Networks It is the study of how to make computers to make sensible decisions and to learn by ordinary experience as we do.
  • 13. Neurons The human brain consists has about 100 billion neurons and 100 trillion connections (synapses) between them. Here is what a typical neuron looks like: Many highly specialized types of neurons exist, and these differ widely in appearance. Characteristically, neurons are highly asymmetric in shape.
  • 14.  It consists of an input layer, one or more hidden layers and an output layer. Input Layer Hidden Layer Output Layer Structure of Multi layer feed forward neural network Multi layer feed forward neural network
  • 15. Backpropagation  Backpropagation is the neural network learning algorithm.  It learns by iteratively processing a dataset of training examples, comparing the network's prediction for each example with the actual known target value.
  • 16. Overview of BP The backpropagation algorithm learns the network by iteratively processing the np training examples of a dataset, comparing the networks result ok for each example with the desired known target value dk for each target class k in a dataset.
  • 17. Consider a fully connected three layer feedforward neural network as in figure , X1 X2 Xi Xl … … … h1 O1 … w11 w12 wl1 wlm hm On v11 v12 vm1 vmn Overviewof BP – Contd. Bias (-1) Bias (-1) h2
  • 18. Consists of l input neurons, m hidden neurons and n output neurons np be the number of examples consider for training.  Let xip be the ith input unit of pth example in a dataset, where i= 1, 2,… l. Wij be the weight between input unit neuron i to hidden unit neuron j, where j=1,2…m, Overview of BP – Contd.
  • 19. vjk be the weight between hidden neuron j to output neuron k, where k=1, 2,… n. initially the weights wij and vjk takes the random value between -1 to 1. Let hj be the activation value of the hidden neuron j ok be the actual output of the kth neuron. Overview of BP – Contd.
  • 20. Bias • It is a threshold value that serves to vary the activity of the neuron. • The bias input is fixed and always equals -1. Overview of BP – Contd.
  • 21. The activation value of hidden neuron hj for pth examples can be calculated by, Overview of BP – Contd.
  • 22. The actual output ok can be calculated by, Overview of SBP – Contd.
  • 23.  Weights are modified for each example so as to minimize the mean squared error (mse).  The value of mse can be calculated according to the following equation Overview of BP – Contd.
  • 24. Weight updation are made in the backward direction i.e., from the output layer through hidden layer and to input layer. Overview of BP – Contd.
  • 25. Learning Rate λ  avoids local minimum (where the weights appear to converge but are not at the optimal solution). encourages finding global minimum. Typically having a value between 0.0 to 1.0. Overview of BP – Contd.
  • 26. For each unit k in the output layer  compute the Error using Errk = ok(1-ok)(dk-ok) For each weight vjk in network  compute weight increment using Δvjk=(λ) Errk*hj  update the weight vjk using vjk = vjk + Δvjk Overview of BP – Contd.
  • 27. For each unit j in the hidden layers, from the last to the first hidden layer compute the Error using Errj = hj (1-hj) Σ Errk*vjk; For each weight wij in network  compute weight increment using Δwij=(λ)*Errj*xip  update the weight wij using wij = wij + Δwij Overview of BP – Contd.
  • 28. Overview of BP – Contd. For each bias Ǿj in network  compute the bias increment using Δ Ǿj = (λ)*Errj  update the bias weight using Ǿj = Ǿj + Δ Ǿj
  • 29. The algorithm stops the learning when, • The mean squared error is below a threshold value. • A pre specified number of epochs has expired Overview of BP – Contd.
  • 30. Random data selection method  The training and testing examples are taken randomly from each class. K-fold cross validation method Example The iris dataset is having 3 classes with 50 examples for each class. From each class 25 examples are taken randomly for training and another 25 examples are taken randomly for testing the network. Data selection method.
  • 31. Performance Measures Accuracy It is the percentage of test dataset that are correctly classified by the classifier. Speed It refers to computational time and cost involved in generating and using given classifier.
  • 32. Evolving Network Architectures The success of ANNs largely depends on their architecture.  Small networks require long training time and can be easily get trapped into a Local Minima.  Large networks able to learn fast and avoids local minima but with poor generalization.  Optimal architecture is a network that is large enough to learn the problem and is small enough to generalize well.
  • 33. approaches for optimizing Neural Networks Constructive methods - new hidden units are added during the training process, also called as Growing methods. Destructive methods - a large network is trained and then unimportant nodes or weights are removed, also called as Pruning methods. Hybrid methods - can both add and remove.
  • 34. Pruning is defined as a network trimming within the assumed initial architecture. This can be accomplished by estimating the sensitivity of the total error to the exclusion of each weight or neuron in the network. The weights or neurons which are insensitive to error changes can be discarded after each step of training. The trimmed network is of smaller size and is likely give higher accuracy than before its trimming. What is Pruning ?
  • 35. Hepatitis Pruning Results Step Current Architecture Acctest % Epochs Pruned Neurons 1 19-25-2 78.2 200 18 hidden neurons 2 19-7-2 80.5 50 5 hidden neurons 3 19-2-2 83.95 50 Pruning stops Original network with architecture 19-25-2 with accuracy 78.2% is reduced to the architecture 19-2-2.  Requires 0.76 seconds to obtain the pruned network.
  • 36. Rule Extraction Why Rule extraction? An important drawback of neural networks is their lack of explanation capability i.e., it is very difficult to understand how an ANN has solved a problem. To overcome this problem various rule extraction algorithms have been developed. Rule extraction : It changes a black box system into a white box system by translating the internal knowledge of a neural network into a set of symbolic rules . The classification process of a neural networks can be described by a set of simple rules.
  • 37. Extracted Rules of 6 real datasets.
  • 38. •robots that can see, feel, and predict the world around them •improved stock prediction •common usage of self-driving cars •composition of music •handwritten documents to be automatically transformed into formatted word processing documents •trends found in the human genome to aid in the understanding of the data compiled by the Human Genome Project •self-diagnosis of medical problems using neural networks and much more! NNs might, in the future, allow: