Artificial Neural Networks for NIU

Prof. Neeta Awasthy
Prof. Neeta AwasthyDirector, GL Bajaj, Mathura à G L Bajaj Group of Institutions, Mathura
Artificial Neural
Networks
14.3.2016
Prof. Neeta Awasthy
Director, School of Engineering and Technology
NOIDA INTERNATIONAL UNVERSITY,
Greater Noida
Course Objective
 To understand, successfully apply
and evaluate Neural Network
structures and paradigms for
problems in Science, Engineering and
Business.
PreRequisites
 It is expected that, the audience has a flair
to understand algorithms and basic
knowledge of Mathematics, Logic gates
and Programming
Outline
 Introduction
 How the human brain learns
 Neuron Models
 Different types of Neural Networks
 Network Layers and Structure
 Training a Neural Network
 Application of ANN
Introduction: Artificial Intelligence
 Artificial Intelligence techniques such as Neural
networks, genetic algorithms and fuzzy logic are
among the most powerful tools available for
detecting and describing subtle relationships in
massive amounts of seemingly unrelated data.
 Neural networks can learn and are actually
taught instead of being programmed.
 Teaching mode can be supervised or
unsupervised
 Neural Networks learn in the presence of noise
How the Human Brain learns
 In the human brain, a typical neuron collects signals from others through a host
of fine structures called dendrites.
 The neuron sends out spikes of electrical activity through a long, thin stand
known as an axon, which splits into thousands of branches.
 At the end of each branch, a structure called a synapse converts the activity from
the axon into electrical effects that inhibit or excite activity in the connected
neurons.
A Neuron Model
 When a neuron receives excitatory input that is sufficiently large
compared with its inhibitory input, it sends a spike of electrical activity
down its axon. Learning occurs by changing the effectiveness of the
synapses so that the influence of one neuron on another changes.
 We conduct these neural networks by first trying to deduce the essential
features of neurons and their interconnections.
 We then typically program a computer to simulate these features.
A Simple Neuron
 An artificial neuron is a device with many inputs and one output.
 The neuron has two modes of operation;
 the training mode and
 the using mode.
The McCulloch-Pitts model
Neurons work by processing information. They receive and provide
information in form of spikes.
Inputs
Output
w2
w1
w3
wn
.
.
.
x1
x2
x3
…
xn-1
xn
y
Properties for Mc Culloch and Pitts Model
Input is 0 or 1
Weights are -1, 0 or +1
Threshold is an integer
Output is 0 or 1
Output is 1 if multiplication of weight and input is more than the threshold
else Outputs 0
Represent the gates NOT, OR and AND with the help of this model
Truth Table
L=0
-1
x
y
x y
0 1
1 0
x=0
The Perceptron Model
The Sigmoidal Function
Linear Separability
OR gate v/s XOR gate
Feed Forward Network
Summary of the simple networks
 Single layer nets have limited representation
power (linear separability problem)
 Error drive seems a good way to train a net
 Multi-layer nets (or nets with non-linear hidden
units) may overcome linear inseparability
problem, learning methods for such nets are
needed
 Threshold/step output functions hinders the
effort to develop learning methods for multi-
layered nets
Types of Problems
 Mathematical Modeling (Function Approximation)
 Classification
 Clustering
 Forecasting
 Vector Quantization
 Pattern Association
 Control
 Optimization
Training/ Learning
 Learning can be of one of the following forms:
 Supervised Learning
 Unsupervised Learning
 Reinforced Learning
 The patterns given to classifier may be on:
 Parametric Estimation
 Non- Parametric Estimation
Machine Learning in ANNs
 Supervised Learning − It involves a
teacher that is scholar than the ANN itself.
For example, the teacher feeds some
example data about which the teacher
already knows the answers.
Machine Learning in ANNs
 Unsupervised Learning − It is required
when there is no example data set with
known answers. For example, searching
for a hidden pattern. In this case, clustering
i.e. dividing a set of elements into groups
according to some unknown pattern is
carried out based on the existing data sets
present.
Machine Learning in ANNs
 Reinforcement Learning − This strategy
built on observation. The ANN makes a
decision by observing its environment. If
the observation is negative, the network
adjusts its weights to be able to make a
different required decision the next time.
Unsupervised Learning: why?
 Collecting and labeling a large set of sample patterns can
be costly.
 Train with large amounts of unlabeled data, and only then
use supervision to label the groupings found.
 In dynamic systems, the samples can change slowly.
 To find features that will then be useful for categorization.
To provide a form of data dependent smart processing or
smart feature extraction.
 To Perform exploratory data analysis, to find structure of
data, to form proper classes for supervised analysis.
Measure of Dissimilarity:
 Define a metric or distance function d on the vector space λ as
a real-valued function on the Cartesian product λX λ such that:
 Positive Definiteness:
0 < d(x,y) < ∞ for x,y ελ and d(x,y)=0 if and only if x=y
 Symmetry:
d(x,y) = d(y,x) for x,y ελ
 Triangular Inequality:
d(x,y) = d(x,z) + d(y,z) for x,y,z ελ
 Invariance or distance function: d(x+z,y+z) = d(x,y)
Error Computation
 Minkowski Matrix or Lk norm
 Manhattan Distance or L1 norm
 Euclidian Distance or L2 norm
 Ln norm
 No Free Lunch Theorem
 No classification method is inherently superior
to any other.Classifier to be decide on the
grounds of type of problem, prior distribution of
samples, training data, cost function.
 Ugly Duckling Theorem
 There is no privileged or ‘best’ feature
representation, and that even the notion of
similarity between patterns depends implicitly
on assumption that may or may not be correct.
Neural networks have performed
successfully where other methods have
not, predicting system behavior,
recognizing and matching complicated,
vague, or incomplete data patterns.
Apply ANNs to pattern recognition,
interpretation, prediction, diagnosis,
planning, monitoring, debugging, repair,
instruction, control
 Biomedical Signal Processing
 Biometric Identification
 Pattern Recognition
 System Reliability
 Business
 Target Tracking
Neural Network Applications
Pattern Recognition System
Sensing Segmentation
Classification (missing
features & context)
Post-processing (costs/
errors)
Feature Extraction
Input
Output (decision)
Artificial Neural Networks for NIU
1 sur 28

Recommandé

Artificial neural networks (2) par
Artificial neural networks (2)Artificial neural networks (2)
Artificial neural networks (2)sai anjaneya
717 vues20 diapositives
Unit+i par
Unit+iUnit+i
Unit+iChetan Dhembre
1.3K vues35 diapositives
Neural network 20161210_jintaekseo par
Neural network 20161210_jintaekseoNeural network 20161210_jintaekseo
Neural network 20161210_jintaekseoJinTaek Seo
457 vues57 diapositives
Ann by rutul mehta par
Ann by rutul mehtaAnn by rutul mehta
Ann by rutul mehtaRutul Mehta
1.2K vues26 diapositives
Neural Networks par
Neural NetworksNeural Networks
Neural NetworksNikitaRuhela
15.3K vues41 diapositives
Artificial Neural Network (draft) par
Artificial Neural Network (draft)Artificial Neural Network (draft)
Artificial Neural Network (draft)James Boulie
2K vues61 diapositives

Contenu connexe

Tendances

Artificial neural networks par
Artificial neural networksArtificial neural networks
Artificial neural networksmadhu sudhakar
502 vues43 diapositives
Neural network par
Neural networkNeural network
Neural networkKRISH na TimeTraveller
9.1K vues23 diapositives
Artificial neural network model & hidden layers in multilayer artificial neur... par
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
5.8K vues40 diapositives
Neural network & its applications par
Neural network & its applications Neural network & its applications
Neural network & its applications Ahmed_hashmi
195.3K vues50 diapositives
Artificial Neural Network par
Artificial Neural NetworkArtificial Neural Network
Artificial Neural NetworkPratik Aggarwal
480 vues33 diapositives
Artifical Neural Network and its applications par
Artifical Neural Network and its applicationsArtifical Neural Network and its applications
Artifical Neural Network and its applicationsSangeeta Tiwari
1.6K vues31 diapositives

Tendances(20)

Artificial neural network model & hidden layers in multilayer artificial neur... par Muhammad Ishaq
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 Ishaq5.8K vues
Neural network & its applications par Ahmed_hashmi
Neural network & its applications Neural network & its applications
Neural network & its applications
Ahmed_hashmi195.3K vues
Artifical Neural Network and its applications par Sangeeta Tiwari
Artifical Neural Network and its applicationsArtifical Neural Network and its applications
Artifical Neural Network and its applications
Sangeeta Tiwari1.6K vues
Artificial Neural Network par Knoldus Inc.
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
Knoldus Inc.5.4K vues
Artificial Neural Networks Lect1: Introduction & neural computation par Mohammed Bennamoun
Artificial Neural Networks Lect1: Introduction & neural computationArtificial Neural Networks Lect1: Introduction & neural computation
Artificial Neural Networks Lect1: Introduction & neural computation
Mohammed Bennamoun4.9K vues
Fundamental, An Introduction to Neural Networks par Nelson Piedra
Fundamental, An Introduction to Neural NetworksFundamental, An Introduction to Neural Networks
Fundamental, An Introduction to Neural Networks
Nelson Piedra5K vues
Artificial Neural Network par Atul Krishna
Artificial Neural NetworkArtificial Neural Network
Artificial Neural Network
Atul Krishna1.3K vues
Ann par vini89
Ann Ann
Ann
vini892.1K vues
Neural networks par Slideshare
Neural networksNeural networks
Neural networks
Slideshare6.9K vues
Neural networks par Basil John
Neural networksNeural networks
Neural networks
Basil John1.5K vues
Comparative study of ANNs and BNNs and mathematical modeling of a neuron par Saransh Choudhary
Comparative study of ANNs and BNNs and mathematical modeling of a neuronComparative study of ANNs and BNNs and mathematical modeling of a neuron
Comparative study of ANNs and BNNs and mathematical modeling of a neuron

En vedette

14. mohsin dalvi artificial neural networks presentation par
14. mohsin dalvi   artificial neural networks presentation14. mohsin dalvi   artificial neural networks presentation
14. mohsin dalvi artificial neural networks presentationPurnesh Aloni
3.1K vues46 diapositives
Artificial neural network par
Artificial neural networkArtificial neural network
Artificial neural networkDEEPASHRI HK
186.6K vues22 diapositives
Fuzzy and nn par
Fuzzy and nnFuzzy and nn
Fuzzy and nnShimi Haridasan
1.6K vues50 diapositives
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKS par
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKSARTIFICIAL INTELLIGENCE & NEURAL NETWORKS
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKSEr Kaushal
13.6K vues26 diapositives
Magnetic levitation par
Magnetic levitationMagnetic levitation
Magnetic levitationervivekdubey
14.8K vues20 diapositives
Final ppt maglev par
Final ppt maglevFinal ppt maglev
Final ppt maglevNazia Banoo Siddiqui
28K vues22 diapositives

En vedette(10)

14. mohsin dalvi artificial neural networks presentation par Purnesh Aloni
14. mohsin dalvi   artificial neural networks presentation14. mohsin dalvi   artificial neural networks presentation
14. mohsin dalvi artificial neural networks presentation
Purnesh Aloni3.1K vues
Artificial neural network par DEEPASHRI HK
Artificial neural networkArtificial neural network
Artificial neural network
DEEPASHRI HK186.6K vues
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKS par Er Kaushal
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKSARTIFICIAL INTELLIGENCE & NEURAL NETWORKS
ARTIFICIAL INTELLIGENCE & NEURAL NETWORKS
Er Kaushal13.6K vues
Magnetic levitation par ervivekdubey
Magnetic levitationMagnetic levitation
Magnetic levitation
ervivekdubey14.8K vues
Artificial intelligence in power systems par Riyas K H
Artificial intelligence in power systems Artificial intelligence in power systems
Artificial intelligence in power systems
Riyas K H23.5K vues
Artificial intelligence NEURAL NETWORKS par REHMAT ULLAH
Artificial intelligence NEURAL NETWORKSArtificial intelligence NEURAL NETWORKS
Artificial intelligence NEURAL NETWORKS
REHMAT ULLAH37.2K vues
Artificial neural networks par stellajoseph
Artificial neural networksArtificial neural networks
Artificial neural networks
stellajoseph48K vues
Data Science - Part VIII - Artifical Neural Network par Derek Kane
Data Science - Part VIII -  Artifical Neural NetworkData Science - Part VIII -  Artifical Neural Network
Data Science - Part VIII - Artifical Neural Network
Derek Kane4.6K vues

Similaire à Artificial Neural Networks for NIU

Artificial neural networks par
Artificial neural networks Artificial neural networks
Artificial neural networks ShwethaShreeS
121 vues24 diapositives
nncollovcapaldo2013-131220052427-phpapp01.pdf par
nncollovcapaldo2013-131220052427-phpapp01.pdfnncollovcapaldo2013-131220052427-phpapp01.pdf
nncollovcapaldo2013-131220052427-phpapp01.pdfGayathriRHICETCSESTA
50 vues42 diapositives
nncollovcapaldo2013-131220052427-phpapp01.pdf par
nncollovcapaldo2013-131220052427-phpapp01.pdfnncollovcapaldo2013-131220052427-phpapp01.pdf
nncollovcapaldo2013-131220052427-phpapp01.pdfGayathriRHICETCSESTA
40 vues42 diapositives
machinelearningengineeringslideshare-160909192132 (1).pdf par
machinelearningengineeringslideshare-160909192132 (1).pdfmachinelearningengineeringslideshare-160909192132 (1).pdf
machinelearningengineeringslideshare-160909192132 (1).pdfShivareddyGangam
5 vues60 diapositives
Applications in Machine Learning par
Applications in Machine LearningApplications in Machine Learning
Applications in Machine LearningJoel Graff
2.5K vues60 diapositives
B42010712 par
B42010712B42010712
B42010712IJERA Editor
514 vues6 diapositives

Similaire à Artificial Neural Networks for NIU(20)

Artificial neural networks par ShwethaShreeS
Artificial neural networks Artificial neural networks
Artificial neural networks
ShwethaShreeS121 vues
machinelearningengineeringslideshare-160909192132 (1).pdf par ShivareddyGangam
machinelearningengineeringslideshare-160909192132 (1).pdfmachinelearningengineeringslideshare-160909192132 (1).pdf
machinelearningengineeringslideshare-160909192132 (1).pdf
Applications in Machine Learning par Joel Graff
Applications in Machine LearningApplications in Machine Learning
Applications in Machine Learning
Joel Graff2.5K vues
Soft Computing-173101 par AMIT KUMAR
Soft Computing-173101Soft Computing-173101
Soft Computing-173101
AMIT KUMAR3.1K vues
X-TREPAN: A MULTI CLASS REGRESSION AND ADAPTED EXTRACTION OF COMPREHENSIBLE D... par 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 vues
X-TREPAN : A Multi Class Regression and Adapted Extraction of Comprehensible ... par 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 vues
Machine Learning: Introduction to Neural Networks par Francesco Collova'
Machine Learning: Introduction to Neural NetworksMachine Learning: Introduction to Neural Networks
Machine Learning: Introduction to Neural Networks
Francesco Collova'16.1K vues
Neuralnetwork 101222074552-phpapp02 par Deepu Gupta
Neuralnetwork 101222074552-phpapp02Neuralnetwork 101222074552-phpapp02
Neuralnetwork 101222074552-phpapp02
Deepu Gupta1.3K vues
X trepan an extended trepan for par ijaia
X trepan an extended trepan forX trepan an extended trepan for
X trepan an extended trepan for
ijaia396 vues
Artificial Neural Networks: Applications In Management par IOSR Journals
Artificial Neural Networks: Applications In ManagementArtificial Neural Networks: Applications In Management
Artificial Neural Networks: Applications In Management
IOSR Journals547 vues

Plus de Prof. Neeta Awasthy

Subhash Chandra Bose, His travels to Freedom par
Subhash Chandra Bose, His travels to FreedomSubhash Chandra Bose, His travels to Freedom
Subhash Chandra Bose, His travels to FreedomProf. Neeta Awasthy
77 vues19 diapositives
# 21 tips for a great presentation par
# 21 tips for a great presentation# 21 tips for a great presentation
# 21 tips for a great presentationProf. Neeta Awasthy
33 vues27 diapositives
Comparative Design thinking par
Comparative Design thinking Comparative Design thinking
Comparative Design thinking Prof. Neeta Awasthy
1.6K vues38 diapositives
National Education Policy 2020 par
National Education Policy 2020 National Education Policy 2020
National Education Policy 2020 Prof. Neeta Awasthy
688 vues41 diapositives
Personalised education (2) par
Personalised education (2)Personalised education (2)
Personalised education (2)Prof. Neeta Awasthy
267 vues7 diapositives
Case study of digitization in india par
Case study of digitization in indiaCase study of digitization in india
Case study of digitization in indiaProf. Neeta Awasthy
142 vues26 diapositives

Plus de Prof. Neeta Awasthy(20)

Academic industry collaboration at kec dated 3.6.17 v 3 par Prof. Neeta Awasthy
Academic industry collaboration at kec dated 3.6.17 v 3Academic industry collaboration at kec dated 3.6.17 v 3
Academic industry collaboration at kec dated 3.6.17 v 3
Artificial Neural Networks for NIU session 2016 17 par Prof. Neeta Awasthy
Artificial Neural Networks for NIU session 2016 17 Artificial Neural Networks for NIU session 2016 17
Artificial Neural Networks for NIU session 2016 17

Dernier

REPRESENTATION - GAUNTLET.pptx par
REPRESENTATION - GAUNTLET.pptxREPRESENTATION - GAUNTLET.pptx
REPRESENTATION - GAUNTLET.pptxiammrhaywood
138 vues26 diapositives
Gross Anatomy of the Liver par
Gross Anatomy of the LiverGross Anatomy of the Liver
Gross Anatomy of the Liverobaje godwin sunday
61 vues12 diapositives
The basics - information, data, technology and systems.pdf par
The basics - information, data, technology and systems.pdfThe basics - information, data, technology and systems.pdf
The basics - information, data, technology and systems.pdfJonathanCovena1
146 vues1 diapositive
The Value and Role of Media and Information Literacy in the Information Age a... par
The Value and Role of Media and Information Literacy in the Information Age a...The Value and Role of Media and Information Literacy in the Information Age a...
The Value and Role of Media and Information Literacy in the Information Age a...Naseej Academy أكاديمية نسيج
58 vues42 diapositives
MIXING OF PHARMACEUTICALS.pptx par
MIXING OF PHARMACEUTICALS.pptxMIXING OF PHARMACEUTICALS.pptx
MIXING OF PHARMACEUTICALS.pptxAnupkumar Sharma
95 vues35 diapositives
Thanksgiving!.pdf par
Thanksgiving!.pdfThanksgiving!.pdf
Thanksgiving!.pdfEnglishCEIPdeSigeiro
264 vues17 diapositives

Dernier(20)

REPRESENTATION - GAUNTLET.pptx par iammrhaywood
REPRESENTATION - GAUNTLET.pptxREPRESENTATION - GAUNTLET.pptx
REPRESENTATION - GAUNTLET.pptx
iammrhaywood138 vues
The basics - information, data, technology and systems.pdf par JonathanCovena1
The basics - information, data, technology and systems.pdfThe basics - information, data, technology and systems.pdf
The basics - information, data, technology and systems.pdf
JonathanCovena1146 vues
CUNY IT Picciano.pptx par apicciano
CUNY IT Picciano.pptxCUNY IT Picciano.pptx
CUNY IT Picciano.pptx
apicciano54 vues
When Sex Gets Complicated: Porn, Affairs, & Cybersex par Marlene Maheu
When Sex Gets Complicated: Porn, Affairs, & CybersexWhen Sex Gets Complicated: Porn, Affairs, & Cybersex
When Sex Gets Complicated: Porn, Affairs, & Cybersex
Marlene Maheu85 vues
ISO/IEC 27001 and ISO/IEC 27005: Managing AI Risks Effectively par PECB
ISO/IEC 27001 and ISO/IEC 27005: Managing AI Risks EffectivelyISO/IEC 27001 and ISO/IEC 27005: Managing AI Risks Effectively
ISO/IEC 27001 and ISO/IEC 27005: Managing AI Risks Effectively
PECB 623 vues
Narration lesson plan par TARIQ KHAN
Narration lesson planNarration lesson plan
Narration lesson plan
TARIQ KHAN61 vues
11.28.23 Social Capital and Social Exclusion.pptx par mary850239
11.28.23 Social Capital and Social Exclusion.pptx11.28.23 Social Capital and Social Exclusion.pptx
11.28.23 Social Capital and Social Exclusion.pptx
mary850239312 vues
Classification of crude drugs.pptx par GayatriPatra14
Classification of crude drugs.pptxClassification of crude drugs.pptx
Classification of crude drugs.pptx
GayatriPatra14101 vues

Artificial Neural Networks for NIU

  • 1. Artificial Neural Networks 14.3.2016 Prof. Neeta Awasthy Director, School of Engineering and Technology NOIDA INTERNATIONAL UNVERSITY, Greater Noida
  • 2. Course Objective  To understand, successfully apply and evaluate Neural Network structures and paradigms for problems in Science, Engineering and Business.
  • 3. PreRequisites  It is expected that, the audience has a flair to understand algorithms and basic knowledge of Mathematics, Logic gates and Programming
  • 4. Outline  Introduction  How the human brain learns  Neuron Models  Different types of Neural Networks  Network Layers and Structure  Training a Neural Network  Application of ANN
  • 5. Introduction: Artificial Intelligence  Artificial Intelligence techniques such as Neural networks, genetic algorithms and fuzzy logic are among the most powerful tools available for detecting and describing subtle relationships in massive amounts of seemingly unrelated data.  Neural networks can learn and are actually taught instead of being programmed.  Teaching mode can be supervised or unsupervised  Neural Networks learn in the presence of noise
  • 6. How the Human Brain learns  In the human brain, a typical neuron collects signals from others through a host of fine structures called dendrites.  The neuron sends out spikes of electrical activity through a long, thin stand known as an axon, which splits into thousands of branches.  At the end of each branch, a structure called a synapse converts the activity from the axon into electrical effects that inhibit or excite activity in the connected neurons.
  • 7. A Neuron Model  When a neuron receives excitatory input that is sufficiently large compared with its inhibitory input, it sends a spike of electrical activity down its axon. Learning occurs by changing the effectiveness of the synapses so that the influence of one neuron on another changes.  We conduct these neural networks by first trying to deduce the essential features of neurons and their interconnections.  We then typically program a computer to simulate these features.
  • 8. A Simple Neuron  An artificial neuron is a device with many inputs and one output.  The neuron has two modes of operation;  the training mode and  the using mode.
  • 9. The McCulloch-Pitts model Neurons work by processing information. They receive and provide information in form of spikes. Inputs Output w2 w1 w3 wn . . . x1 x2 x3 … xn-1 xn y
  • 10. Properties for Mc Culloch and Pitts Model Input is 0 or 1 Weights are -1, 0 or +1 Threshold is an integer Output is 0 or 1 Output is 1 if multiplication of weight and input is more than the threshold else Outputs 0 Represent the gates NOT, OR and AND with the help of this model Truth Table L=0 -1 x y x y 0 1 1 0 x=0
  • 14. OR gate v/s XOR gate
  • 16. Summary of the simple networks  Single layer nets have limited representation power (linear separability problem)  Error drive seems a good way to train a net  Multi-layer nets (or nets with non-linear hidden units) may overcome linear inseparability problem, learning methods for such nets are needed  Threshold/step output functions hinders the effort to develop learning methods for multi- layered nets
  • 17. Types of Problems  Mathematical Modeling (Function Approximation)  Classification  Clustering  Forecasting  Vector Quantization  Pattern Association  Control  Optimization
  • 18. Training/ Learning  Learning can be of one of the following forms:  Supervised Learning  Unsupervised Learning  Reinforced Learning  The patterns given to classifier may be on:  Parametric Estimation  Non- Parametric Estimation
  • 19. Machine Learning in ANNs  Supervised Learning − It involves a teacher that is scholar than the ANN itself. For example, the teacher feeds some example data about which the teacher already knows the answers.
  • 20. Machine Learning in ANNs  Unsupervised Learning − It is required when there is no example data set with known answers. For example, searching for a hidden pattern. In this case, clustering i.e. dividing a set of elements into groups according to some unknown pattern is carried out based on the existing data sets present.
  • 21. Machine Learning in ANNs  Reinforcement Learning − This strategy built on observation. The ANN makes a decision by observing its environment. If the observation is negative, the network adjusts its weights to be able to make a different required decision the next time.
  • 22. Unsupervised Learning: why?  Collecting and labeling a large set of sample patterns can be costly.  Train with large amounts of unlabeled data, and only then use supervision to label the groupings found.  In dynamic systems, the samples can change slowly.  To find features that will then be useful for categorization. To provide a form of data dependent smart processing or smart feature extraction.  To Perform exploratory data analysis, to find structure of data, to form proper classes for supervised analysis.
  • 23. Measure of Dissimilarity:  Define a metric or distance function d on the vector space λ as a real-valued function on the Cartesian product λX λ such that:  Positive Definiteness: 0 < d(x,y) < ∞ for x,y ελ and d(x,y)=0 if and only if x=y  Symmetry: d(x,y) = d(y,x) for x,y ελ  Triangular Inequality: d(x,y) = d(x,z) + d(y,z) for x,y,z ελ  Invariance or distance function: d(x+z,y+z) = d(x,y)
  • 24. Error Computation  Minkowski Matrix or Lk norm  Manhattan Distance or L1 norm  Euclidian Distance or L2 norm  Ln norm
  • 25.  No Free Lunch Theorem  No classification method is inherently superior to any other.Classifier to be decide on the grounds of type of problem, prior distribution of samples, training data, cost function.  Ugly Duckling Theorem  There is no privileged or ‘best’ feature representation, and that even the notion of similarity between patterns depends implicitly on assumption that may or may not be correct.
  • 26. Neural networks have performed successfully where other methods have not, predicting system behavior, recognizing and matching complicated, vague, or incomplete data patterns. Apply ANNs to pattern recognition, interpretation, prediction, diagnosis, planning, monitoring, debugging, repair, instruction, control  Biomedical Signal Processing  Biometric Identification  Pattern Recognition  System Reliability  Business  Target Tracking Neural Network Applications
  • 27. Pattern Recognition System Sensing Segmentation Classification (missing features & context) Post-processing (costs/ errors) Feature Extraction Input Output (decision)