SlideShare a Scribd company logo
1 of 18
Download to read offline
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
DOI : 10.5121/ijist.2016.6212 105
MATHEMATICAL EXPLANATION TO
SOLUTION FOR EX-NOR PROBLEM USING
MLFFN
Vaibhav Kant Singh
Department of Computer Science and Engineering, Institute of Technology, Guru
Ghasidas Vishwavidyalaya, Central University, Bilaspur,Chhattisgarh,India
ABSTRACT
This paper is in continuation to what we did previously in the field of Soft Computing. In the previous work
the author proposed several solutions to the XOR problem. In this paper we will see some solutions to the
Ex-NOR problem using the concept of MLFFN. Ex-NOR problem is a non-linearly separable problem the
solutions of which are discussed in this paper. The Artificial Neural Network proposed is mathematically
proved to be successful in providing solution to the Ex-NOR problem. The solutions proposed are
explained by means of Architectural Graph and Signal flow graph.
KEYWORDS
Artificial Neural Network, Ex-NOR, Activation function, Signal Flow Graph & Architectural Graph
1.INTRODUCTION
Soft Computing is the branch of Computer Science that deals with methodologies that solve the
problems which portray imprecision, partial truth and uncertainty. In Soft Computing the
impression is tolerable. Computational time when compared with Hard Computing is less due to
the presence of intelligent computational steps. Soft Computing involves systems which are
basically inspired from nature like Artificial Neural Network and Fuzzy Logic. The programs
made are going to follow new laws which are going to justify the logic behind the programming
done. The output produced need not to be deterministic in nature. It may allow parallel
computation. It is capable to produce approximate result to the problem posed by the user. Soft
Computing is basically a branch that deals with three known streams for the implementation of
the idea that it portrays. The three streams are Artificial Neural Network, Fuzzy Systems and
Genetic Algorithm and Evolutionary Programming.
In this paper the author Vaibhav Kant Singh focuses on the stream Artificial Neural Network.
Artificial Neural Network (ANN) is a stream that deals with construction of systems which are
having analogy in working with the Biological Neural Network working. The ANN systems are
capable of mapping input to output. ANN systems are capable to get trained; they are capable to
learn from previous examples. ANN is capable of generalization. ANN having resemblance with
Biological Network of Neurons are robust and fault tolerant in nature. Some currently existing
ANN systems are Adaptive Resonance Theory (ART), Bidirectional Associative Memory
(BAM), Perceptron (Single Layer and Multilayer), ADALINE and MADALINE, Counter
Propagation Network, Multi Layer Feed Forward Network (MLFFN), Hopfield Network,
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
106
Necognition, Self-Organizing feature map, Brain-State-In-A-Box, BPN, Boltzmann machines etc.
Artificial Neural Network systems comprises of three basic elements namely the Individual
neurons present in the ANN, the network topology (the network architecture) and the learning
algorithm employed to train the ANN.
2. LITERATURE SURVEY
In [1] Vaibhav Kant Singh proposed one solution to the XOR problem using MLP. In [2]
Vaibhav Kant Singh proposed two other solutions to the XOR problem. In [3] Vaibhav Kant
Singh proposed solutions to the various logic gates. In [4] Vaibhav Kant Singh gave a survey to
the various learning techniques employed for training the Artificial Neural Network. In [5,6]
Vaibhav Kant Singh proposed another solution to the XOR problem using minimum
configuration MLP.
3.PROBLEM STATEMENT
The Ex-NOR problem is non-linearly separable problem. The Definition of linear separability is
two sets of points A and B in an n-dimensional space are called linearly separable if (n+1) real
numbers 1, 2โ€ฆ ( +1)exists, such that every point (x1,x2 ......xn) โˆˆA satisfies
=1โ‰ฅ ( +1)exist and every point ( 1, 2โ€ฆ )โˆˆ satisfies =1< ( +1) exist. Table
1 represents the Ex-NOR logic and the Figure in Table 1 specifies the portrayal of the inputs
applicable for Ex-NOR problem in Two-dimensional plane. It is very clear from the table that it is
not possible to divide the inputs into two classes on the basis of output. Thus from the research
that the author Vaibhav Kant Singh [1,2,5] made earlier the problem is a non-linearly separable
problem.
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
107
4.PROPOSED SOLUTIONS
In this paper we will see some solutions to the Ex-NOR problem using MLFFN.
4.1.First Proposed Solution to the Ex-NOR problem
In first proposed solution a MLFFN is proposed which comprises of three layers. The First layer
comprises of two neurons. The second layer comprises of one neuron. The third layer comprises
of one neuron. The first layer comprises of non-linear neuron. The second and third layer
comprises of neurons which are having linear in nature. The neurons are characterized linear and
non-linear on the basis of the characteristic they exhibit. The naming of the network could be (2-
2-1-1). The solution proposed specifies the final values for weights acquired after training the
network. After attaining the values prescribed in the solution the proposed ANN gives the desired
values for output for the applicable input to the Ex-NOR logic GATE. In this section wewill see
the mathematical proof of the provided solution. Figure 1 represents the proposed Architectural
Graph for the problem, whereas the Figure 2 represents the Signal Flow Graph giving the detail
of the weights and other parameters involved in the ANN. In the Architectural graph NL
represents nonlinear whereas LE represents Linear element. Z represents the output produced by
the ANN.
Figure1: Architectural Graph representing First and Third Solution to Ex-NOR Problem
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
108
Figure2: Signal Flow Graph representing First Solution to Ex-NOR Problem
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
109
The value produced by node5 in Eq(9) will be squashed by the linear activation function i.e. the
threshold function. Since, in the output layer the neuron present exhibits linear characteristics in
minimum configuration MLFFN. Definition of Threshold function is :-
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
110
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
111
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
112
4.2.Second Proposed Solution to the Ex-NOR problem
Figure 3. Architectural graph representing the second solution to the Ex-NOR problem using MLFFN
In this section we will see the second proposed solution to the Ex-NOR problem. The proposed
solution is a MLFFN comprising of three layers. Each layer comprises of one neuron each. The
first layer comprises of one neuron. The neuron in layer one is non-linear. The neuron in layer
two and three are linear in nature. Figure 3 and Figure 4 represent Architectural Graph and Signal
Flow Graph for the proposed solution.
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
113
Figure4. Signal flow graph representing the second solution to the Ex-NOR problem using MLFFN
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
114
In this case for output neuron which is linear element we will be using threshold function as the
activation function. The threshold value is 1.35. The definition of Threshold function is:-
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
115
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
116
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
117
4.3.Third Proposed Solution to the Ex-NOR problem
Figure5. Signal flow graph representing the third solution to the Ex-NOR problem using MLFFN
In Third proposed solution a MLFFN is proposed which comprises of three layers. The First layer
comprises of two neurons. The second layer comprises of one neuron. The third layer comprises
of one neuron. The first layer comprises of non-linear neuron. The second and third layer
comprises of neurons which are having linear in nature. The neurons are characterized linear and
non-linear on the basis of the characteristic they exhibit. The naming of the network could be (2-
2-1-1). The solution proposed specifies the final values for weights acquired after training the
network. After attaining the values prescribed in the solution the proposed ANN gives the desired
values for output for the applicable input to the Ex-NOR logic GATE. In this section we will see
the mathematical proof of the provided solution. Figure 1 represents the proposed Architectural
Graph for the problem, whereas the Figure 5 represents the Signal Flow Graph giving the detail
of the weights and other parameters involved in the ANN. In the Architectural graph NL
represents nonlinear whereas LE represents Linear element. Z represents the output produced by
the ANN.
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
118
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
119
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
120
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
121
3. CONCLUSIONS
In this paper two solutions to the Ex-NOR problem is proposed using the MLFFN. From the
proposed solutions it is clear that it is possible to solve non-linearly separable problem using
Multilayer Network. All the proposed solutions comprises of three layers where the elements in
the network may be of either type i.e. Non-linear or Linear. The mathematical proof satisfies the
condition for Ex-NOR.
International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016
122
ACKNOWLEDGEMENTS
I would like to place my thanks to my mother Smt Sushma Singh, my wife Smt Shubhra Singh,
my brothers Abhinav Kant Singh and Abhuday Kant Singh, my sister Priyamvada Singh , my
daughter Akshi and son Aishwaryat for the support that they give for the preparation of this work.
Last but not the least I want to thank my Father Late Shri Triveni Kant Singh for his blessing,
which enabled me to this work.
REFERENCES
[1] Vaibhav Kant Singh, (2015) โ€œOne Solution to XOR problem using Multilayer Perceptron having
Minimum Configurationโ€ International Journal of Science and Engineering, Vol. 3, No. 2, pp 32-41.
[2] Vaibhav Kant Singh, (2015) โ€œTwo Solutions to the XOR Problem using minimum configuration
MLPโ€, International Journal of Advanced Engineering Science and Technological Research, Vol. 3,
No. 3, pp16-20.
[3] Vaibhav Kant Singh (2016) โ€œANN Implementation of Constructing Logic Gates Focusing On Ex-
NORโ€, Innovations in Computation, Communication and Cybernetics, Proceeding of BITCON 2016,
Department of Computer Science & Engineering, BIT, Durg, Chhattisgarh, India.
[4] Vaibhav Kant Singh (2016) โ€œMathematical Analysis For Training ANNs Using Basic Learning
Algorithmsโ€, Innovations in Computation, Communication and Cybernetics, Proceeding of BITCON
2016, Department of Computer Science & Engineering, BIT, Durg, Chhattisgarh, India.
[5] Vaibhav Kant Singh, (2016) โ€œProposing solution to XOR problem using minimum configuration
MLPโ€, To Appear Procedia of Elsevier, International Conference on Computational Modeling and
Security (CMS 2016), Bangalore, India.
[6] Vaibhav Kant Singh and Shweta Pandey, (2016) โ€œMinimum Configuration MLP for Solving XOR
Problem,โ€ To Appear in IEEE Explore, Proceeding of the 10th INDIACom: INDIACom-2016, 3rd
2016 International Conference on โ€œComputing for Sustainable Global Development,โ€ BVICAM, New
Delhi, India.
Author
Vaibhav Kant Singh, [LM ISTE] and [LM CSI] is currently working as
Assistant Professor in the Department of Computer Science & Engineering,
Institute of Technology, Guru Ghasidas Vishwavidyalaya, (Central University),
Bilaspur, (C.G.), India. He is having around Eight years of teaching experience.
He is having papers published in both international and national conferences.
His papers are published in national and international journals too. His Papers
are published by Publishers like Springer, ACM, AIP, WASET, Recently one
paper Accepted for Publication in Elsevier, One paper accepted in first round for publication in
IEEE Explore etc. In International Conferences papers are published in Conferences organized by
IITโ€™s, IIITโ€™s, CSI, WASET etc. He has taught several subjects like, AI and Expert System, Data
Mining, Soft Computing (ANN, Genetic Algorithm and Fuzzy Logic), Network Programming,
Compiler Design, Advanced Programming through JAVA, OOP through C++, Prolog, Lisp,
Internet Fundamentals and Application, Parallel Computing, Operating System,DAA etc.

More Related Content

Similar to MATHEMATICAL EXPLANATION TO SOLUTION FOR EX-NOR PROBLEM USING MLFFN

DESIGN AND IMPLEMENTATION OF BINARY NEURAL NETWORK LEARNING WITH FUZZY CLUSTE...
DESIGN AND IMPLEMENTATION OF BINARY NEURAL NETWORK LEARNING WITH FUZZY CLUSTE...DESIGN AND IMPLEMENTATION OF BINARY NEURAL NETWORK LEARNING WITH FUZZY CLUSTE...
DESIGN AND IMPLEMENTATION OF BINARY NEURAL NETWORK LEARNING WITH FUZZY CLUSTE...cscpconf
ย 
20141003.journal club
20141003.journal club20141003.journal club
20141003.journal clubHayaru SHOUNO
ย 
Predictive Metabonomics
Predictive MetabonomicsPredictive Metabonomics
Predictive MetabonomicsMarilyn Arceo
ย 
Multilayer Backpropagation Neural Networks for Implementation of Logic Gates
Multilayer Backpropagation Neural Networks for Implementation of Logic GatesMultilayer Backpropagation Neural Networks for Implementation of Logic Gates
Multilayer Backpropagation Neural Networks for Implementation of Logic GatesIJCSES Journal
ย 
Electricity consumption-prediction-model-using neuro-fuzzy-system
Electricity consumption-prediction-model-using neuro-fuzzy-systemElectricity consumption-prediction-model-using neuro-fuzzy-system
Electricity consumption-prediction-model-using neuro-fuzzy-systemCemal Ardil
ย 
Optimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionOptimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionIAEME Publication
ย 
Optimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionOptimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionIAEME Publication
ย 
Optimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionOptimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionIAEME Publication
ย 
JACT 5-3_Christakis
JACT 5-3_ChristakisJACT 5-3_Christakis
JACT 5-3_ChristakisVasilis Barbaris
ย 
Expert system design for elastic scattering neutrons optical model using bpnn
Expert system design for elastic scattering neutrons optical model using bpnnExpert system design for elastic scattering neutrons optical model using bpnn
Expert system design for elastic scattering neutrons optical model using bpnnijcsa
ย 
Incorporating Kalman Filter in the Optimization of Quantum Neural Network Par...
Incorporating Kalman Filter in the Optimization of Quantum Neural Network Par...Incorporating Kalman Filter in the Optimization of Quantum Neural Network Par...
Incorporating Kalman Filter in the Optimization of Quantum Neural Network Par...Waqas Tariq
ย 
A Mixed Binary-Real NSGA II Algorithm Ensuring Both Accuracy and Interpretabi...
A Mixed Binary-Real NSGA II Algorithm Ensuring Both Accuracy and Interpretabi...A Mixed Binary-Real NSGA II Algorithm Ensuring Both Accuracy and Interpretabi...
A Mixed Binary-Real NSGA II Algorithm Ensuring Both Accuracy and Interpretabi...IJECEIAES
ย 
Implementation of Feed Forward Neural Network for Classification by Education...
Implementation of Feed Forward Neural Network for Classification by Education...Implementation of Feed Forward Neural Network for Classification by Education...
Implementation of Feed Forward Neural Network for Classification by Education...ijsrd.com
ย 
New Approach of Preprocessing For Numeral Recognition
New Approach of Preprocessing For Numeral RecognitionNew Approach of Preprocessing For Numeral Recognition
New Approach of Preprocessing For Numeral RecognitionIJERA Editor
ย 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)IJERD Editor
ย 
A SURVEY OF ARTIFICIAL NEURAL NETWORKS APPLICATIONS IN WEAR AND MANUFACTURING...
A SURVEY OF ARTIFICIAL NEURAL NETWORKS APPLICATIONS IN WEAR AND MANUFACTURING...A SURVEY OF ARTIFICIAL NEURAL NETWORKS APPLICATIONS IN WEAR AND MANUFACTURING...
A SURVEY OF ARTIFICIAL NEURAL NETWORKS APPLICATIONS IN WEAR AND MANUFACTURING...Monique Carr
ย 
Paper id 24201464
Paper id 24201464Paper id 24201464
Paper id 24201464IJRAT
ย 
Application of Artificial Neural Networking for Determining the Plane of Vibr...
Application of Artificial Neural Networking for Determining the Plane of Vibr...Application of Artificial Neural Networking for Determining the Plane of Vibr...
Application of Artificial Neural Networking for Determining the Plane of Vibr...IOSRJMCE
ย 
Paper id 252014146
Paper id 252014146Paper id 252014146
Paper id 252014146IJRAT
ย 
A survey research summary on neural networks
A survey research summary on neural networksA survey research summary on neural networks
A survey research summary on neural networkseSAT Publishing House
ย 

Similar to MATHEMATICAL EXPLANATION TO SOLUTION FOR EX-NOR PROBLEM USING MLFFN (20)

DESIGN AND IMPLEMENTATION OF BINARY NEURAL NETWORK LEARNING WITH FUZZY CLUSTE...
DESIGN AND IMPLEMENTATION OF BINARY NEURAL NETWORK LEARNING WITH FUZZY CLUSTE...DESIGN AND IMPLEMENTATION OF BINARY NEURAL NETWORK LEARNING WITH FUZZY CLUSTE...
DESIGN AND IMPLEMENTATION OF BINARY NEURAL NETWORK LEARNING WITH FUZZY CLUSTE...
ย 
20141003.journal club
20141003.journal club20141003.journal club
20141003.journal club
ย 
Predictive Metabonomics
Predictive MetabonomicsPredictive Metabonomics
Predictive Metabonomics
ย 
Multilayer Backpropagation Neural Networks for Implementation of Logic Gates
Multilayer Backpropagation Neural Networks for Implementation of Logic GatesMultilayer Backpropagation Neural Networks for Implementation of Logic Gates
Multilayer Backpropagation Neural Networks for Implementation of Logic Gates
ย 
Electricity consumption-prediction-model-using neuro-fuzzy-system
Electricity consumption-prediction-model-using neuro-fuzzy-systemElectricity consumption-prediction-model-using neuro-fuzzy-system
Electricity consumption-prediction-model-using neuro-fuzzy-system
ย 
Optimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionOptimal neural network models for wind speed prediction
Optimal neural network models for wind speed prediction
ย 
Optimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionOptimal neural network models for wind speed prediction
Optimal neural network models for wind speed prediction
ย 
Optimal neural network models for wind speed prediction
Optimal neural network models for wind speed predictionOptimal neural network models for wind speed prediction
Optimal neural network models for wind speed prediction
ย 
JACT 5-3_Christakis
JACT 5-3_ChristakisJACT 5-3_Christakis
JACT 5-3_Christakis
ย 
Expert system design for elastic scattering neutrons optical model using bpnn
Expert system design for elastic scattering neutrons optical model using bpnnExpert system design for elastic scattering neutrons optical model using bpnn
Expert system design for elastic scattering neutrons optical model using bpnn
ย 
Incorporating Kalman Filter in the Optimization of Quantum Neural Network Par...
Incorporating Kalman Filter in the Optimization of Quantum Neural Network Par...Incorporating Kalman Filter in the Optimization of Quantum Neural Network Par...
Incorporating Kalman Filter in the Optimization of Quantum Neural Network Par...
ย 
A Mixed Binary-Real NSGA II Algorithm Ensuring Both Accuracy and Interpretabi...
A Mixed Binary-Real NSGA II Algorithm Ensuring Both Accuracy and Interpretabi...A Mixed Binary-Real NSGA II Algorithm Ensuring Both Accuracy and Interpretabi...
A Mixed Binary-Real NSGA II Algorithm Ensuring Both Accuracy and Interpretabi...
ย 
Implementation of Feed Forward Neural Network for Classification by Education...
Implementation of Feed Forward Neural Network for Classification by Education...Implementation of Feed Forward Neural Network for Classification by Education...
Implementation of Feed Forward Neural Network for Classification by Education...
ย 
New Approach of Preprocessing For Numeral Recognition
New Approach of Preprocessing For Numeral RecognitionNew Approach of Preprocessing For Numeral Recognition
New Approach of Preprocessing For Numeral Recognition
ย 
International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)International Journal of Engineering Research and Development (IJERD)
International Journal of Engineering Research and Development (IJERD)
ย 
A SURVEY OF ARTIFICIAL NEURAL NETWORKS APPLICATIONS IN WEAR AND MANUFACTURING...
A SURVEY OF ARTIFICIAL NEURAL NETWORKS APPLICATIONS IN WEAR AND MANUFACTURING...A SURVEY OF ARTIFICIAL NEURAL NETWORKS APPLICATIONS IN WEAR AND MANUFACTURING...
A SURVEY OF ARTIFICIAL NEURAL NETWORKS APPLICATIONS IN WEAR AND MANUFACTURING...
ย 
Paper id 24201464
Paper id 24201464Paper id 24201464
Paper id 24201464
ย 
Application of Artificial Neural Networking for Determining the Plane of Vibr...
Application of Artificial Neural Networking for Determining the Plane of Vibr...Application of Artificial Neural Networking for Determining the Plane of Vibr...
Application of Artificial Neural Networking for Determining the Plane of Vibr...
ย 
Paper id 252014146
Paper id 252014146Paper id 252014146
Paper id 252014146
ย 
A survey research summary on neural networks
A survey research summary on neural networksA survey research summary on neural networks
A survey research summary on neural networks
ย 

More from ijistjournal

International Journal of Information Sciences and Techniques (IJIST)
International Journal of Information Sciences and Techniques (IJIST)International Journal of Information Sciences and Techniques (IJIST)
International Journal of Information Sciences and Techniques (IJIST)ijistjournal
ย 
BRAIN TUMOR MRIIMAGE CLASSIFICATION WITH FEATURE SELECTION AND EXTRACTION USI...
BRAIN TUMOR MRIIMAGE CLASSIFICATION WITH FEATURE SELECTION AND EXTRACTION USI...BRAIN TUMOR MRIIMAGE CLASSIFICATION WITH FEATURE SELECTION AND EXTRACTION USI...
BRAIN TUMOR MRIIMAGE CLASSIFICATION WITH FEATURE SELECTION AND EXTRACTION USI...ijistjournal
ย 
Research Article Submission - International Journal of Information Sciences a...
Research Article Submission - International Journal of Information Sciences a...Research Article Submission - International Journal of Information Sciences a...
Research Article Submission - International Journal of Information Sciences a...ijistjournal
ย 
A MEDIAN BASED DIRECTIONAL CASCADED WITH MASK FILTER FOR REMOVAL OF RVIN
A MEDIAN BASED DIRECTIONAL CASCADED WITH MASK FILTER FOR REMOVAL OF RVINA MEDIAN BASED DIRECTIONAL CASCADED WITH MASK FILTER FOR REMOVAL OF RVIN
A MEDIAN BASED DIRECTIONAL CASCADED WITH MASK FILTER FOR REMOVAL OF RVINijistjournal
ย 
DECEPTION AND RACISM IN THE TUSKEGEE SYPHILIS STUDY
DECEPTION AND RACISM IN THE TUSKEGEE  SYPHILIS STUDYDECEPTION AND RACISM IN THE TUSKEGEE  SYPHILIS STUDY
DECEPTION AND RACISM IN THE TUSKEGEE SYPHILIS STUDYijistjournal
ย 
Online Paper Submission - International Journal of Information Sciences and T...
Online Paper Submission - International Journal of Information Sciences and T...Online Paper Submission - International Journal of Information Sciences and T...
Online Paper Submission - International Journal of Information Sciences and T...ijistjournal
ย 
A NOVEL APPROACH FOR SEGMENTATION OF SECTOR SCAN SONAR IMAGES USING ADAPTIVE ...
A NOVEL APPROACH FOR SEGMENTATION OF SECTOR SCAN SONAR IMAGES USING ADAPTIVE ...A NOVEL APPROACH FOR SEGMENTATION OF SECTOR SCAN SONAR IMAGES USING ADAPTIVE ...
A NOVEL APPROACH FOR SEGMENTATION OF SECTOR SCAN SONAR IMAGES USING ADAPTIVE ...ijistjournal
ย 
Call for Papers - International Journal of Information Sciences and Technique...
Call for Papers - International Journal of Information Sciences and Technique...Call for Papers - International Journal of Information Sciences and Technique...
Call for Papers - International Journal of Information Sciences and Technique...ijistjournal
ย 
Online Paper Submission - 4th International Conference on NLP & Data Mining (...
Online Paper Submission - 4th International Conference on NLP & Data Mining (...Online Paper Submission - 4th International Conference on NLP & Data Mining (...
Online Paper Submission - 4th International Conference on NLP & Data Mining (...ijistjournal
ย 
TOWARDS AUTOMATIC DETECTION OF SENTIMENTS IN CUSTOMER REVIEWS
TOWARDS AUTOMATIC DETECTION OF SENTIMENTS IN CUSTOMER REVIEWSTOWARDS AUTOMATIC DETECTION OF SENTIMENTS IN CUSTOMER REVIEWS
TOWARDS AUTOMATIC DETECTION OF SENTIMENTS IN CUSTOMER REVIEWSijistjournal
ย 
Research Articles Submission - International Journal of Information Sciences ...
Research Articles Submission - International Journal of Information Sciences ...Research Articles Submission - International Journal of Information Sciences ...
Research Articles Submission - International Journal of Information Sciences ...ijistjournal
ย 
ANALYSIS OF IMAGE WATERMARKING USING LEAST SIGNIFICANT BIT ALGORITHM
ANALYSIS OF IMAGE WATERMARKING USING LEAST SIGNIFICANT BIT ALGORITHMANALYSIS OF IMAGE WATERMARKING USING LEAST SIGNIFICANT BIT ALGORITHM
ANALYSIS OF IMAGE WATERMARKING USING LEAST SIGNIFICANT BIT ALGORITHMijistjournal
ย 
Call for Research Articles - 6th International Conference on Machine Learning...
Call for Research Articles - 6th International Conference on Machine Learning...Call for Research Articles - 6th International Conference on Machine Learning...
Call for Research Articles - 6th International Conference on Machine Learning...ijistjournal
ย 
Online Paper Submission - International Journal of Information Sciences and T...
Online Paper Submission - International Journal of Information Sciences and T...Online Paper Submission - International Journal of Information Sciences and T...
Online Paper Submission - International Journal of Information Sciences and T...ijistjournal
ย 
Colour Image Steganography Based on Pixel Value Differencing in Spatial Domain
Colour Image Steganography Based on Pixel Value Differencing in Spatial DomainColour Image Steganography Based on Pixel Value Differencing in Spatial Domain
Colour Image Steganography Based on Pixel Value Differencing in Spatial Domainijistjournal
ย 
Call for Research Articles - 5th International conference on Advanced Natural...
Call for Research Articles - 5th International conference on Advanced Natural...Call for Research Articles - 5th International conference on Advanced Natural...
Call for Research Articles - 5th International conference on Advanced Natural...ijistjournal
ย 
International Journal of Information Sciences and Techniques (IJIST)
International Journal of Information Sciences and Techniques (IJIST)International Journal of Information Sciences and Techniques (IJIST)
International Journal of Information Sciences and Techniques (IJIST)ijistjournal
ย 
Research Article Submission - International Journal of Information Sciences a...
Research Article Submission - International Journal of Information Sciences a...Research Article Submission - International Journal of Information Sciences a...
Research Article Submission - International Journal of Information Sciences a...ijistjournal
ย 
Design and Implementation of LZW Data Compression Algorithm
Design and Implementation of LZW Data Compression AlgorithmDesign and Implementation of LZW Data Compression Algorithm
Design and Implementation of LZW Data Compression Algorithmijistjournal
ย 
Online Paper Submission - 5th International Conference on Soft Computing, Art...
Online Paper Submission - 5th International Conference on Soft Computing, Art...Online Paper Submission - 5th International Conference on Soft Computing, Art...
Online Paper Submission - 5th International Conference on Soft Computing, Art...ijistjournal
ย 

More from ijistjournal (20)

International Journal of Information Sciences and Techniques (IJIST)
International Journal of Information Sciences and Techniques (IJIST)International Journal of Information Sciences and Techniques (IJIST)
International Journal of Information Sciences and Techniques (IJIST)
ย 
BRAIN TUMOR MRIIMAGE CLASSIFICATION WITH FEATURE SELECTION AND EXTRACTION USI...
BRAIN TUMOR MRIIMAGE CLASSIFICATION WITH FEATURE SELECTION AND EXTRACTION USI...BRAIN TUMOR MRIIMAGE CLASSIFICATION WITH FEATURE SELECTION AND EXTRACTION USI...
BRAIN TUMOR MRIIMAGE CLASSIFICATION WITH FEATURE SELECTION AND EXTRACTION USI...
ย 
Research Article Submission - International Journal of Information Sciences a...
Research Article Submission - International Journal of Information Sciences a...Research Article Submission - International Journal of Information Sciences a...
Research Article Submission - International Journal of Information Sciences a...
ย 
A MEDIAN BASED DIRECTIONAL CASCADED WITH MASK FILTER FOR REMOVAL OF RVIN
A MEDIAN BASED DIRECTIONAL CASCADED WITH MASK FILTER FOR REMOVAL OF RVINA MEDIAN BASED DIRECTIONAL CASCADED WITH MASK FILTER FOR REMOVAL OF RVIN
A MEDIAN BASED DIRECTIONAL CASCADED WITH MASK FILTER FOR REMOVAL OF RVIN
ย 
DECEPTION AND RACISM IN THE TUSKEGEE SYPHILIS STUDY
DECEPTION AND RACISM IN THE TUSKEGEE  SYPHILIS STUDYDECEPTION AND RACISM IN THE TUSKEGEE  SYPHILIS STUDY
DECEPTION AND RACISM IN THE TUSKEGEE SYPHILIS STUDY
ย 
Online Paper Submission - International Journal of Information Sciences and T...
Online Paper Submission - International Journal of Information Sciences and T...Online Paper Submission - International Journal of Information Sciences and T...
Online Paper Submission - International Journal of Information Sciences and T...
ย 
A NOVEL APPROACH FOR SEGMENTATION OF SECTOR SCAN SONAR IMAGES USING ADAPTIVE ...
A NOVEL APPROACH FOR SEGMENTATION OF SECTOR SCAN SONAR IMAGES USING ADAPTIVE ...A NOVEL APPROACH FOR SEGMENTATION OF SECTOR SCAN SONAR IMAGES USING ADAPTIVE ...
A NOVEL APPROACH FOR SEGMENTATION OF SECTOR SCAN SONAR IMAGES USING ADAPTIVE ...
ย 
Call for Papers - International Journal of Information Sciences and Technique...
Call for Papers - International Journal of Information Sciences and Technique...Call for Papers - International Journal of Information Sciences and Technique...
Call for Papers - International Journal of Information Sciences and Technique...
ย 
Online Paper Submission - 4th International Conference on NLP & Data Mining (...
Online Paper Submission - 4th International Conference on NLP & Data Mining (...Online Paper Submission - 4th International Conference on NLP & Data Mining (...
Online Paper Submission - 4th International Conference on NLP & Data Mining (...
ย 
TOWARDS AUTOMATIC DETECTION OF SENTIMENTS IN CUSTOMER REVIEWS
TOWARDS AUTOMATIC DETECTION OF SENTIMENTS IN CUSTOMER REVIEWSTOWARDS AUTOMATIC DETECTION OF SENTIMENTS IN CUSTOMER REVIEWS
TOWARDS AUTOMATIC DETECTION OF SENTIMENTS IN CUSTOMER REVIEWS
ย 
Research Articles Submission - International Journal of Information Sciences ...
Research Articles Submission - International Journal of Information Sciences ...Research Articles Submission - International Journal of Information Sciences ...
Research Articles Submission - International Journal of Information Sciences ...
ย 
ANALYSIS OF IMAGE WATERMARKING USING LEAST SIGNIFICANT BIT ALGORITHM
ANALYSIS OF IMAGE WATERMARKING USING LEAST SIGNIFICANT BIT ALGORITHMANALYSIS OF IMAGE WATERMARKING USING LEAST SIGNIFICANT BIT ALGORITHM
ANALYSIS OF IMAGE WATERMARKING USING LEAST SIGNIFICANT BIT ALGORITHM
ย 
Call for Research Articles - 6th International Conference on Machine Learning...
Call for Research Articles - 6th International Conference on Machine Learning...Call for Research Articles - 6th International Conference on Machine Learning...
Call for Research Articles - 6th International Conference on Machine Learning...
ย 
Online Paper Submission - International Journal of Information Sciences and T...
Online Paper Submission - International Journal of Information Sciences and T...Online Paper Submission - International Journal of Information Sciences and T...
Online Paper Submission - International Journal of Information Sciences and T...
ย 
Colour Image Steganography Based on Pixel Value Differencing in Spatial Domain
Colour Image Steganography Based on Pixel Value Differencing in Spatial DomainColour Image Steganography Based on Pixel Value Differencing in Spatial Domain
Colour Image Steganography Based on Pixel Value Differencing in Spatial Domain
ย 
Call for Research Articles - 5th International conference on Advanced Natural...
Call for Research Articles - 5th International conference on Advanced Natural...Call for Research Articles - 5th International conference on Advanced Natural...
Call for Research Articles - 5th International conference on Advanced Natural...
ย 
International Journal of Information Sciences and Techniques (IJIST)
International Journal of Information Sciences and Techniques (IJIST)International Journal of Information Sciences and Techniques (IJIST)
International Journal of Information Sciences and Techniques (IJIST)
ย 
Research Article Submission - International Journal of Information Sciences a...
Research Article Submission - International Journal of Information Sciences a...Research Article Submission - International Journal of Information Sciences a...
Research Article Submission - International Journal of Information Sciences a...
ย 
Design and Implementation of LZW Data Compression Algorithm
Design and Implementation of LZW Data Compression AlgorithmDesign and Implementation of LZW Data Compression Algorithm
Design and Implementation of LZW Data Compression Algorithm
ย 
Online Paper Submission - 5th International Conference on Soft Computing, Art...
Online Paper Submission - 5th International Conference on Soft Computing, Art...Online Paper Submission - 5th International Conference on Soft Computing, Art...
Online Paper Submission - 5th International Conference on Soft Computing, Art...
ย 

Recently uploaded

College Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service NashikCollege Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service NashikCall Girls in Nagpur High Profile
ย 
Processing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptxProcessing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptxpranjaldaimarysona
ย 
Glass Ceramics: Processing and Properties
Glass Ceramics: Processing and PropertiesGlass Ceramics: Processing and Properties
Glass Ceramics: Processing and PropertiesPrabhanshu Chaturvedi
ย 
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls in Nagpur High Profile
ย 
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...Call Girls in Nagpur High Profile
ย 
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur High Profile
ย 
result management system report for college project
result management system report for college projectresult management system report for college project
result management system report for college projectTonystark477637
ย 
MANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTING
MANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTINGMANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTING
MANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTINGSIVASHANKAR N
ย 
Online banking management system project.pdf
Online banking management system project.pdfOnline banking management system project.pdf
Online banking management system project.pdfKamal Acharya
ย 
UNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its PerformanceUNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its Performancesivaprakash250
ย 
Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)simmis5
ย 
Introduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxIntroduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxupamatechverse
ย 
UNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular ConduitsUNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular Conduitsrknatarajan
ย 
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordCCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordAsst.prof M.Gokilavani
ย 
Introduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxIntroduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxupamatechverse
ย 
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...roncy bisnoi
ย 
AKTU Computer Networks notes --- Unit 3.pdf
AKTU Computer Networks notes ---  Unit 3.pdfAKTU Computer Networks notes ---  Unit 3.pdf
AKTU Computer Networks notes --- Unit 3.pdfankushspencer015
ย 
BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptx
BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptxBSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptx
BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptxfenichawla
ย 
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls in Nagpur High Profile
ย 

Recently uploaded (20)

College Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service NashikCollege Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
College Call Girls Nashik Nehal 7001305949 Independent Escort Service Nashik
ย 
Processing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptxProcessing & Properties of Floor and Wall Tiles.pptx
Processing & Properties of Floor and Wall Tiles.pptx
ย 
Glass Ceramics: Processing and Properties
Glass Ceramics: Processing and PropertiesGlass Ceramics: Processing and Properties
Glass Ceramics: Processing and Properties
ย 
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service NashikCall Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
Call Girls Service Nashik Vaishnavi 7001305949 Independent Escort Service Nashik
ย 
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...Booking open Available Pune Call Girls Koregaon Park  6297143586 Call Hot Ind...
Booking open Available Pune Call Girls Koregaon Park 6297143586 Call Hot Ind...
ย 
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur EscortsHigh Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
High Profile Call Girls Nagpur Meera Call 7001035870 Meet With Nagpur Escorts
ย 
result management system report for college project
result management system report for college projectresult management system report for college project
result management system report for college project
ย 
MANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTING
MANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTINGMANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTING
MANUFACTURING PROCESS-II UNIT-1 THEORY OF METAL CUTTING
ย 
Online banking management system project.pdf
Online banking management system project.pdfOnline banking management system project.pdf
Online banking management system project.pdf
ย 
UNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its PerformanceUNIT - IV - Air Compressors and its Performance
UNIT - IV - Air Compressors and its Performance
ย 
Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)Java Programming :Event Handling(Types of Events)
Java Programming :Event Handling(Types of Events)
ย 
Introduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptxIntroduction and different types of Ethernet.pptx
Introduction and different types of Ethernet.pptx
ย 
UNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular ConduitsUNIT-II FMM-Flow Through Circular Conduits
UNIT-II FMM-Flow Through Circular Conduits
ย 
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete RecordCCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
CCS335 _ Neural Networks and Deep Learning Laboratory_Lab Complete Record
ย 
Introduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptxIntroduction to Multiple Access Protocol.pptx
Introduction to Multiple Access Protocol.pptx
ย 
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
Call Girls Pimpri Chinchwad Call Me 7737669865 Budget Friendly No Advance Boo...
ย 
Roadmap to Membership of RICS - Pathways and Routes
Roadmap to Membership of RICS - Pathways and RoutesRoadmap to Membership of RICS - Pathways and Routes
Roadmap to Membership of RICS - Pathways and Routes
ย 
AKTU Computer Networks notes --- Unit 3.pdf
AKTU Computer Networks notes ---  Unit 3.pdfAKTU Computer Networks notes ---  Unit 3.pdf
AKTU Computer Networks notes --- Unit 3.pdf
ย 
BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptx
BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptxBSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptx
BSides Seattle 2024 - Stopping Ethan Hunt From Taking Your Data.pptx
ย 
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur EscortsCall Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
Call Girls Service Nagpur Tanvi Call 7001035870 Meet With Nagpur Escorts
ย 

MATHEMATICAL EXPLANATION TO SOLUTION FOR EX-NOR PROBLEM USING MLFFN

  • 1. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 DOI : 10.5121/ijist.2016.6212 105 MATHEMATICAL EXPLANATION TO SOLUTION FOR EX-NOR PROBLEM USING MLFFN Vaibhav Kant Singh Department of Computer Science and Engineering, Institute of Technology, Guru Ghasidas Vishwavidyalaya, Central University, Bilaspur,Chhattisgarh,India ABSTRACT This paper is in continuation to what we did previously in the field of Soft Computing. In the previous work the author proposed several solutions to the XOR problem. In this paper we will see some solutions to the Ex-NOR problem using the concept of MLFFN. Ex-NOR problem is a non-linearly separable problem the solutions of which are discussed in this paper. The Artificial Neural Network proposed is mathematically proved to be successful in providing solution to the Ex-NOR problem. The solutions proposed are explained by means of Architectural Graph and Signal flow graph. KEYWORDS Artificial Neural Network, Ex-NOR, Activation function, Signal Flow Graph & Architectural Graph 1.INTRODUCTION Soft Computing is the branch of Computer Science that deals with methodologies that solve the problems which portray imprecision, partial truth and uncertainty. In Soft Computing the impression is tolerable. Computational time when compared with Hard Computing is less due to the presence of intelligent computational steps. Soft Computing involves systems which are basically inspired from nature like Artificial Neural Network and Fuzzy Logic. The programs made are going to follow new laws which are going to justify the logic behind the programming done. The output produced need not to be deterministic in nature. It may allow parallel computation. It is capable to produce approximate result to the problem posed by the user. Soft Computing is basically a branch that deals with three known streams for the implementation of the idea that it portrays. The three streams are Artificial Neural Network, Fuzzy Systems and Genetic Algorithm and Evolutionary Programming. In this paper the author Vaibhav Kant Singh focuses on the stream Artificial Neural Network. Artificial Neural Network (ANN) is a stream that deals with construction of systems which are having analogy in working with the Biological Neural Network working. The ANN systems are capable of mapping input to output. ANN systems are capable to get trained; they are capable to learn from previous examples. ANN is capable of generalization. ANN having resemblance with Biological Network of Neurons are robust and fault tolerant in nature. Some currently existing ANN systems are Adaptive Resonance Theory (ART), Bidirectional Associative Memory (BAM), Perceptron (Single Layer and Multilayer), ADALINE and MADALINE, Counter Propagation Network, Multi Layer Feed Forward Network (MLFFN), Hopfield Network,
  • 2. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 106 Necognition, Self-Organizing feature map, Brain-State-In-A-Box, BPN, Boltzmann machines etc. Artificial Neural Network systems comprises of three basic elements namely the Individual neurons present in the ANN, the network topology (the network architecture) and the learning algorithm employed to train the ANN. 2. LITERATURE SURVEY In [1] Vaibhav Kant Singh proposed one solution to the XOR problem using MLP. In [2] Vaibhav Kant Singh proposed two other solutions to the XOR problem. In [3] Vaibhav Kant Singh proposed solutions to the various logic gates. In [4] Vaibhav Kant Singh gave a survey to the various learning techniques employed for training the Artificial Neural Network. In [5,6] Vaibhav Kant Singh proposed another solution to the XOR problem using minimum configuration MLP. 3.PROBLEM STATEMENT The Ex-NOR problem is non-linearly separable problem. The Definition of linear separability is two sets of points A and B in an n-dimensional space are called linearly separable if (n+1) real numbers 1, 2โ€ฆ ( +1)exists, such that every point (x1,x2 ......xn) โˆˆA satisfies =1โ‰ฅ ( +1)exist and every point ( 1, 2โ€ฆ )โˆˆ satisfies =1< ( +1) exist. Table 1 represents the Ex-NOR logic and the Figure in Table 1 specifies the portrayal of the inputs applicable for Ex-NOR problem in Two-dimensional plane. It is very clear from the table that it is not possible to divide the inputs into two classes on the basis of output. Thus from the research that the author Vaibhav Kant Singh [1,2,5] made earlier the problem is a non-linearly separable problem.
  • 3. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 107 4.PROPOSED SOLUTIONS In this paper we will see some solutions to the Ex-NOR problem using MLFFN. 4.1.First Proposed Solution to the Ex-NOR problem In first proposed solution a MLFFN is proposed which comprises of three layers. The First layer comprises of two neurons. The second layer comprises of one neuron. The third layer comprises of one neuron. The first layer comprises of non-linear neuron. The second and third layer comprises of neurons which are having linear in nature. The neurons are characterized linear and non-linear on the basis of the characteristic they exhibit. The naming of the network could be (2- 2-1-1). The solution proposed specifies the final values for weights acquired after training the network. After attaining the values prescribed in the solution the proposed ANN gives the desired values for output for the applicable input to the Ex-NOR logic GATE. In this section wewill see the mathematical proof of the provided solution. Figure 1 represents the proposed Architectural Graph for the problem, whereas the Figure 2 represents the Signal Flow Graph giving the detail of the weights and other parameters involved in the ANN. In the Architectural graph NL represents nonlinear whereas LE represents Linear element. Z represents the output produced by the ANN. Figure1: Architectural Graph representing First and Third Solution to Ex-NOR Problem
  • 4. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 108 Figure2: Signal Flow Graph representing First Solution to Ex-NOR Problem
  • 5. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 109 The value produced by node5 in Eq(9) will be squashed by the linear activation function i.e. the threshold function. Since, in the output layer the neuron present exhibits linear characteristics in minimum configuration MLFFN. Definition of Threshold function is :-
  • 6. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 110
  • 7. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 111
  • 8. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 112 4.2.Second Proposed Solution to the Ex-NOR problem Figure 3. Architectural graph representing the second solution to the Ex-NOR problem using MLFFN In this section we will see the second proposed solution to the Ex-NOR problem. The proposed solution is a MLFFN comprising of three layers. Each layer comprises of one neuron each. The first layer comprises of one neuron. The neuron in layer one is non-linear. The neuron in layer two and three are linear in nature. Figure 3 and Figure 4 represent Architectural Graph and Signal Flow Graph for the proposed solution.
  • 9. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 113 Figure4. Signal flow graph representing the second solution to the Ex-NOR problem using MLFFN
  • 10. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 114 In this case for output neuron which is linear element we will be using threshold function as the activation function. The threshold value is 1.35. The definition of Threshold function is:-
  • 11. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 115
  • 12. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 116
  • 13. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 117 4.3.Third Proposed Solution to the Ex-NOR problem Figure5. Signal flow graph representing the third solution to the Ex-NOR problem using MLFFN In Third proposed solution a MLFFN is proposed which comprises of three layers. The First layer comprises of two neurons. The second layer comprises of one neuron. The third layer comprises of one neuron. The first layer comprises of non-linear neuron. The second and third layer comprises of neurons which are having linear in nature. The neurons are characterized linear and non-linear on the basis of the characteristic they exhibit. The naming of the network could be (2- 2-1-1). The solution proposed specifies the final values for weights acquired after training the network. After attaining the values prescribed in the solution the proposed ANN gives the desired values for output for the applicable input to the Ex-NOR logic GATE. In this section we will see the mathematical proof of the provided solution. Figure 1 represents the proposed Architectural Graph for the problem, whereas the Figure 5 represents the Signal Flow Graph giving the detail of the weights and other parameters involved in the ANN. In the Architectural graph NL represents nonlinear whereas LE represents Linear element. Z represents the output produced by the ANN.
  • 14. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 118
  • 15. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 119
  • 16. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 120
  • 17. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 121 3. CONCLUSIONS In this paper two solutions to the Ex-NOR problem is proposed using the MLFFN. From the proposed solutions it is clear that it is possible to solve non-linearly separable problem using Multilayer Network. All the proposed solutions comprises of three layers where the elements in the network may be of either type i.e. Non-linear or Linear. The mathematical proof satisfies the condition for Ex-NOR.
  • 18. International Journal of Information Sciences and Techniques (IJIST) Vol.6, No.1/2, March 2016 122 ACKNOWLEDGEMENTS I would like to place my thanks to my mother Smt Sushma Singh, my wife Smt Shubhra Singh, my brothers Abhinav Kant Singh and Abhuday Kant Singh, my sister Priyamvada Singh , my daughter Akshi and son Aishwaryat for the support that they give for the preparation of this work. Last but not the least I want to thank my Father Late Shri Triveni Kant Singh for his blessing, which enabled me to this work. REFERENCES [1] Vaibhav Kant Singh, (2015) โ€œOne Solution to XOR problem using Multilayer Perceptron having Minimum Configurationโ€ International Journal of Science and Engineering, Vol. 3, No. 2, pp 32-41. [2] Vaibhav Kant Singh, (2015) โ€œTwo Solutions to the XOR Problem using minimum configuration MLPโ€, International Journal of Advanced Engineering Science and Technological Research, Vol. 3, No. 3, pp16-20. [3] Vaibhav Kant Singh (2016) โ€œANN Implementation of Constructing Logic Gates Focusing On Ex- NORโ€, Innovations in Computation, Communication and Cybernetics, Proceeding of BITCON 2016, Department of Computer Science & Engineering, BIT, Durg, Chhattisgarh, India. [4] Vaibhav Kant Singh (2016) โ€œMathematical Analysis For Training ANNs Using Basic Learning Algorithmsโ€, Innovations in Computation, Communication and Cybernetics, Proceeding of BITCON 2016, Department of Computer Science & Engineering, BIT, Durg, Chhattisgarh, India. [5] Vaibhav Kant Singh, (2016) โ€œProposing solution to XOR problem using minimum configuration MLPโ€, To Appear Procedia of Elsevier, International Conference on Computational Modeling and Security (CMS 2016), Bangalore, India. [6] Vaibhav Kant Singh and Shweta Pandey, (2016) โ€œMinimum Configuration MLP for Solving XOR Problem,โ€ To Appear in IEEE Explore, Proceeding of the 10th INDIACom: INDIACom-2016, 3rd 2016 International Conference on โ€œComputing for Sustainable Global Development,โ€ BVICAM, New Delhi, India. Author Vaibhav Kant Singh, [LM ISTE] and [LM CSI] is currently working as Assistant Professor in the Department of Computer Science & Engineering, Institute of Technology, Guru Ghasidas Vishwavidyalaya, (Central University), Bilaspur, (C.G.), India. He is having around Eight years of teaching experience. He is having papers published in both international and national conferences. His papers are published in national and international journals too. His Papers are published by Publishers like Springer, ACM, AIP, WASET, Recently one paper Accepted for Publication in Elsevier, One paper accepted in first round for publication in IEEE Explore etc. In International Conferences papers are published in Conferences organized by IITโ€™s, IIITโ€™s, CSI, WASET etc. He has taught several subjects like, AI and Expert System, Data Mining, Soft Computing (ANN, Genetic Algorithm and Fuzzy Logic), Network Programming, Compiler Design, Advanced Programming through JAVA, OOP through C++, Prolog, Lisp, Internet Fundamentals and Application, Parallel Computing, Operating System,DAA etc.