One Solution to XOR problem using Multilayer Perceptron having Minimum Configuration

Size: px
Start display at page:

Download "One Solution to XOR problem using Multilayer Perceptron having Minimum Configuration"

Transcription

1 International Journal of Science and Engineering Volume 3, Number PP: IJSE Available at ISSN: One Solution to XOR problem using Multilayer Perceptron having Minimum Configuration Vaibhav Kant Singh Department of Computer Science and Engineering Institute of Technology, Guru Ghasidas Vishwavidyalaya, Central University, Bilaspur, (C.G.), India 1 Abstract- Artificial Neural Network (ANN) is the branch of Computer Science which deals with the Construction of programs that are having analogy with the Biological Neural Network (BNN). There are various types of ANN systems which are used to solve variety of problems. When we will look into the history of development ANN we saw the concept of linear separabilty. The problems which are supposed to be linearly separable are solved easily my making use of Single layer perceptron model proposed by Rosenblatt. XOR problem the solution to which is discussed in this paper is a nonlinearly separable problem. The problem is a complex problem and requires new type of ANN system for its solution. In this paper we will see Architectural Graph and Signal Flow Graphs representing the ANN equivalent to Minimum Configuration Multilayer perceptron (MLP). We have utilized hyperbolic tangent function as a Activation function for Hidden Layers and Threshold Function as Activation Function for Output Layer. The learning employed is Error Correction Learning and the algorithm employed is Back propagation Algorithm (BPN). In this paper one solution is proposed for the solution of XOR problem. Keywords ANN, BNN, Activation Function, Hyperbolic Tangent Function, BPN, MLP. I. INTRODUCTION TO ARTIFICIAL NEURAL NETWORK Artificial Neural Network is a parallel and distributed processor which is simulated in a digital computer and whose working is analogous to the working of Human Brain. Humans are having nervous system that performs operation in parallel after attaining inputs from the five basic sense organs. The cells which are responsible for processing the stimulus obtained by the environment are called nerve cells or neurons. ANN resembles human brain in two aspects i.e. knowledge is acquired from the environment through an interactive process of weight change and inter-neuron connection strength i.e. synaptic weights are used to store the acquired knowledge. With every iteration of the learning process the ANN becomes more knowledgeable about the environment in which it is operating. ANN are represented using three techniques namely Block diagram representation, Signal flow graph and Architectural Graph. The basic components of a neuron are set of adjustable synaptic weigths attached to the inputs and bias, a Summing Junction and a linear or non-linear activation function. The three basic elements of any ANN are neuron, network topology and learning algorithm. The learning algorithms employed in ANN is classified into three basic types in first level i.e. Supervised learning, Reinforcement learning and Unsupervised learning. Under supervised learning comes Error Correction and Stochastic learning. Error correction is further classified into LMS and BPN. Unsupervised learning on the other hand is classified into Hebbian and Competitive learning. Some of the Neural Network Systems include SOFM (Self Organizing Feature Map), Perceptron, MLP, Neoconition, ADALINE (Adaptive Linear Neural Element), MADALINE (Multiple ADALINE), LVQ (Learning Vector Quantization), AM (Associative Memory), BAM (Bidirectional Associative Memory), Boltzmann machine, BSB (Brain-State-in-a- Box), Cauchy machines, Hopfield network, ART (Adaptive Resonance Theory), RBF (Radial Basis Function), RNN (Recurrent Neural Network) etc. II. SOLUTION OF AND, OR, NAND AND NOR GATES USING MCCULLOCH AND PITTS MODEL (1) AND GATE A.B LOGIC for AND GATE Where A and B are input values

2 One Solution to XOR problem using Multilayer Perceptron having Minimum Configuration Figure 1. Block Diagram Representing a model of single neuron in ANN displaying the solution for AND, OR, NOR, NAND GATES vk=( xi.wi+bk)=uk+bk and Since uk= xi.wi So, from the Neural Network framework we are able to analyze that there are four parameters which are required for generating output yk i.e. A, B, W1 and W2.Therefore the truth-table for the AND, OR, NAND and NOR GATE is given below:- Table -1 Truth Table of AND,OR,NAND and NOR GATE A B (AND) =. (OR) = + (NAND) =. (NOR) = In this case we will be using threshold function as the activation function. The definition of Threshold function is:- 1 if vk 2 Ψ vk = =where 2 is the Threshold value 0 if vk<2 Table -2 Derivation of Solution of AND GATE using single neuron in ANN Now, we will consider the four input patterns, Taking W1=W2=1 and B k=0 a) When, A=0, B=0, W1=1, W2=1 Since vk= xi.wi=aw1+bw2=0x1+0x1=0 Since 0<2 therefore Ψ(vk)=yk=0 Therefore, yk=0 when A=0 and B=0 b) When, A=0, B=1, W1=1, W2=1 Since vk= xi.wi=aw1+bw2=0x1+1x1=1 Since 1<2 therefore Ψ(vk)=yk=0 Therefore, yk=0 when A=0 and B=1 c) When, A=1, B=0, W1=1, W2=1 Since vk= xi.wi=aw1+bw2=1x1+0x1=1 Since 1<2 therefore Ψ(vk)=yk=0 Therefore, yk=0 when A=1 and B=0 d) When, A=1, B=1, W1=1, W2=1 Since vk= xi.wi=aw1+bw2=1x1+1x1=2 Since 2=2 therefore Ψ(vk)=yk=1 Therefore, yk=1 when A=1 and B=1 From Table-2 we are able to conclude that when W1=W2=1 and threshold value set to 2 we are able to find a solution for construction of ANN equivalent to AND GATE. (2) OR GATE A+B LOGIC for AND GATE Where A and B are input values vk=( xi.wi+bk)=uk+bk and Since uk= xi.wi In this case we will be using threshold function as the activation function. The definition of Threshold function is:-

3 IJSE,Volume 3, Number 2 V K Singh 1 if vk 1 Ψ vk = =where 1 is the Threshold value 0 if vk<1 Table -3 Derivation of Solution of OR GATE using single neuron in ANN Now, we will consider the four input patterns, Taking W1=W2=1 and B k=0 a) When, A=0, B=0, W1=1, W2=1 Since vk= xi.wi=aw1+bw2=0x1+0x1=0 Since 0<2 therefore Ψ(vk)=yk=0 Therefore, yk=0 when A=0 and B=0 b) When, A=0, B=1, W1=1, W2=1 Since vk= xi.wi=aw1+bw2=0x1+1x1=1 Since 1=1 therefore Ψ(vk)=yk=1 Therefore, yk=1 when A=0 and B=1 c) When, A=1, B=0, W1=1, W2=1 Since vk= xi.wi=aw1+bw2=1x1+0x1=1 Since 1=1 therefore Ψ(vk)=yk=1 Therefore, yk=1 when A=1 and B=0 d) When, A=1, B=1, W1=1, W2=1 Since vk= xi.wi=aw1+bw2=1x1+1x1=2 Since 2>1 therefore Ψ(vk)=yk=1 Therefore, yk=1 when A=1 and B=1 From Table-3 we are able to conclude that when W1=W2=1 and threshold value set to 1 we are able to find a solution for construction of ANN equivalent to OR GATE. (3) NAND GATE. LOGIC for NAND GATE vk=( xi.wi+bk)=uk+bk and Since uk= xi.wi Where A and B are input values In this case we will be using threshold function as the activation function. The definition of Threshold function is:- 1 if vk 1 Ψ vk = =where 1 is the Threshold value 0 if vk< 1 Table -4 Derivation of Solution of NAND GATE using single neuron in ANN Now, we will consider the four input patterns, Taking W1=W2=-1 and B k=0 a) When, A=0, B=0, W1=-1, W2=-1 Since vk= xi.wi=aw1+bw2=0x-1+0x-1=0 Since 0>-1 therefore Ψ(vk)=yk=1 Therefore, yk=1 when A=0 and B=0 b) When, A=0, B=1, W1=-1, W2=-1 Since vk= xi.wi=aw1+bw2=0x-1+1x-1=-1 Since -1=-1 therefore Ψ(vk)=yk=1 Therefore, yk=1 when A=0 and B=1 c) When, A=1, B=0, W1=1, W2=1 Since vk= xi.wi=aw1+bw2=1x-1+0x-1=-1 Since -1=-1 therefore Ψ(vk)=yk=1 Therefore, yk=1 when A=1 and B=0 d) When, A=1, B=1, W1=-1, W2=-1 Since vk= xi.wi=aw1+bw2=1x-1+1x-1=-2 Since -2<-1 therefore Ψ(vk)=yk=0 Therefore, yk=0 when A=1 and B=1 From Table-4 we are able to conclude that when W1=W2=-1 and threshold value set to -1 we are able to find a solution for construction of ANN equivalent to NAND GATE. (4) NOR GATE LOGIC + for NOR GATE vk=( xi.wi+bk)=uk+bk and Since uk= xi.wi Where A and B are input values In this case we will be using threshold function as the activation function. The definition of Threshold function is:-

4 One Solution to XOR problem using Multilayer Perceptron having Minimum Configuration 1 if vk 0 Ψ vk = =where 0 is the Threshold value 0 if vk<0 Table -5 Derivation of Solution of NOR GATE using single neuron in ANN Now, we will consider the four input patterns, Taking W1=W2=-1 and B k=0 a) When, A=0, B=0, W1=-1, W2=-1 Since vk= xi.wi=aw1+bw2=0x-1+0x-1=0 Since 0=0 therefore Ψ(vk)=yk=1 Therefore, yk=1 when A=0 and B=0 b) When, A=0, B=1, W1=-1, W2=-1 Since vk= xi.wi=aw1+bw2=0x-1+1x-1=-1 Since -1<0 therefore Ψ(vk)=yk=0 Therefore, yk=0 when A=0 and B=1 c) When, A=1, B=0, W1=-1, W2=-1 Since vk= xi.wi=aw1+bw2=1x1+0x1=-1 Since -1<0 therefore Ψ(vk)=yk=0 Therefore, yk=0 when A=1 and B=0 d) When, A=1, B=1, W1=-1, W2=-1 Since vk= xi.wi=aw1+bw2=1x-1+1x-1=-2 Since -2<0 therefore Ψ(vk)=yk=0 Therefore, yk=0 when A=1 and B=1 From Table-5 we are able to conclude that when W1=W2=-1 and threshold value set to 0 we are able to find a solution for construction of ANN equivalent to NOR GATE. III. PROBLEM STATEMENT The solutions proposed for the problems in the above section are portraying a domain which exhibits a common characteristic. The common characteristic which is exhibited is called Linear Separability. 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 w1, w2, w(n+1) exist, such that every point x1,x2.xn satisfies +1 exist, and every point x1,x2.xn satisfies < +1. Rosenblatt in 1958 proposed perceptron model for solving the problems which are linearly separable using supervised learning algorithm which was named perceptron convergence algorithm. Since XOR is a non-linearly separable problem thus require special proposal for its solution. Since, the outputs that XOR produce can t make classification of the inputs using one line in two dimensions. Table -6 Representation of the Inputs in two dimension separated into two classes on the basis of the output that it produce a)graph representing the Linear separablity in AND and NAND GATE where inputs could be classified into classes. b)graph representing the Linear separablity in OR and NOR GATE where inputs could be classified into classes. IV. LITERATURE SURVEY In [1] Abu and Jaques showed the information capacity of general form of memory is formalized. Estimation is made of the number of bits of information that can be stored in the Hopfield model of Associative Memory. In [2] Amari proposed an advance theory of learning and self-organization, covering backpropagation and its generalization as well as the formation of topological maps and neural representations of information. In [3] Akaike reviewed the classical maximum likelihood estimation procedure and a new estimate minimum information theoretical criterion (AIC) estimate (MAICE) which is designed for the purpose of statistical identification is introduced. In [4] Atiya and

5 IJSE,Volume 3, Number 2 V K Singh Abu developed a method for the storage of analog vectors i.e. vectors whose components are real valued, the method is developed for the Hopfield continuous-time network. In [5] Barron established an approximation of properties of a class of ANN. It is shown that Feedforward networks with one layer of sigmoidal non linearities achieve integrated squared errors of order O(1/n), where n is the number of nodes. In [6] Bruck showed the convergence properties of the Hopfield model are dependent on the structure of the interconnection matrix w and the method by which the nodes are updated. In [7] Freeman aim is to emplify the two nodes of information, described in the paper. In [8] the authors proposed a theoretical framework for backpropagation (BP) in order to identify some of its limitation as a general learning procedure and the reasons for its success in several experiments on pattern recognition. In [9] Giles et. al. proved that one method, recurrent cascade correlation, due to its topology has fundamental limitations in representation and there in its learning capabilities. In [10] Cardoso and Laheld introduced a class of adaptive algorithms for source separation which implements an adaptive versions of equivalent estimation and is henceforth called EASI. In [11] the authors Feldkamp and Puskorius presented a coherent neural net based framework for solving various signal processing problem. V. MULTILAYER PERCEPTRON Multilayer Perceptron as the name implies concerns with multiple layers of Neurons. Generally there are three distinguishing feature of Multilayer perceptron which are:- A. Generally the neurons present in the Neural Network are non-linear i.e. the activation function used at each neuron is generally non-linear. Sigmoid function is generally used as activation function. Logistic function or hyperbolic tangent function is used as activation function. B. The neurons present in the network offers a high degree of Connectivity. Generally the neurons present in the network are fully connected. Between the networks the input nodes may directly make connection with the output node. First hidden layer may have connection with the third hidden layer and several variations of this sort may exist between the neurons of the MLP. C. In MLP the Hidden neurons are meant to achieve higher order statistics. Either you may increase the number hidden neurons in the same layer or the number of hidden layers may be increased to transform the problem into simpler form. The learning algorithm used in the case of Multilayer perceptron is called Back Propagation Network (BPN) algorithm. BPN is a type of supervised learning algorithm. It employs error correction learning. BPN comprises of two passes in its framework. Forward pass and Backward pass. In forward pass for the current set of Input actual output is generated. Then since the learning is supervised learning and that too error correction learning, Actual output is compared with the desired output. If error is acknowledged in the forward pass. The error invokes control mechanism which will propagate weight change in the network in backward direction. The procedure continues until the system i.e. ANN learns all the patterns applicable for that domain. BPN training network requires the following steps: STEP1: Select the next training pair from the training set; apply the input vector to the network input. STEP2: Calculate the output of the network. STEP3: Calculate the error between the network output (the target vector from the training pair). STEP4: Adjust the weights of the network in a way that minimizes the error. STEP5: Repeat Steps1 through 4 for each vector in the training set until the error for the entire set is acceptably low. The Correction applied to Wji(n) is defined by the delta rule = Here, η=learning rate constant and ξ(n)=cost function or instantaneous value of error energy.

6 One Solution to XOR problem using Multilayer Perceptron having Minimum Configuration Figure 2. Architectural Graph Representing MLP having two hidden layers VI. MINIMUM CONFIGURATION MULTILAYER PERCEPTRON Figure 3. Architectural Graph Representing MLP having minimum configuration i.e. in the output layer linear activation function could be used MLP beside of having multiple layers in which every element exhibits non linearity by virtue of non linear activation function, provides a variant where there could be one or more hidden layer with Non linear element whereas in the output layer there are going to be linear elements. It means in Minimum configuration MLP in the output layer there could be one or more linear neurons.

7 IJSE,Volume 3, Number 2 V K Singh VII. FIRST SOLUTION TO THE XOR PROBLEM USING MINIMUM CONFIGURATION MULTILAYER PERCEPTRON Figure 4. Architectural Graph Representing MLP having minimum configuration for one solution to XOR problem described below Table -7 Truth Table for XOR GATE x1 x2 = In the first solution for XOR problem in the hidden layer two neurons are present in the proposed solution the activation function used is hyperbolic tangent function. In the output layer the activation function used is Threshold function. The Derivation of the Solution to the XOR problem is given below for the four possible inputs. Figure 5 is having the internal configuration of the MLP. Figure 5 is used to derive the solution. Figure 5. Signal flow graph representing First solution to XOR problem using minimum configuration MLP In the first solution for XOR problem in the hidden layer two neurons are present in the proposed solution the activation function used is hyperbolic tangent function. In the output layer the activation function used is Threshold function. The Derivation of the Solution to the XOR problem is given below for the four possible inputs. Figure 5 is having the internal configuration of the MLP. Figure 5 is used to derive the solution.

8 One Solution to XOR problem using Multilayer Perceptron having Minimum Configuration CASE 1:- When x1=0 and x2=0, At node 1 value of signal will be (1) = = 0.5..(2) At node 2 Signal value will be (3) = = 0.5..(4) Here, the activation function used for hidden layer is Hyperbolic tangent function. The Def. of which is given below:- tanh = sinh 1 = 1 cosh = + = e e h = x=induced local field value, e= The natural logarithm base also known as Euler s number & Range=[-1,+1] At node 3 the signal value will be from Eq(2and 5) = 0.5 = = = At node 4 the signal value will be from Eq (4 and 5) = 0.5 = = = At node 5 the signal value will be from Eq 6 and Eq 7= = = In the output layer the function used is Threshold function. The Definition of the threshold function is given below:- 1 h h = h h h < h h From Eq(9) and Eq(10) the value of output for the first case i.e. x1=0 and x2=0 will be = =0, h h < CASE 2:- When x1=1 and x2=0, At node 1 value of signal will be h 1 2 = = 0.5 (12) At node 2 Signal value will be , h 1 2 = = 1.5..(13) At node 3 the signal value will be from Eq(12and 5) = 0.5 = = = At node 4 the signal value will be from Eq (13 and 5) = 1.5 = = = At node 5 the signal value will be from Eq 14, Eq. 15 and Eq 8 = = From Eq(16) and Eq(10) the value of output for the second case i.e. x1=1 and x2=0 will be =1, h h >

9 IJSE,Volume 3, Number 2 V K Singh CASE 3:- When x1=0 and x2=1, At node 1 value of signal will be h 1 2 = = 1.5 (18) At node 2 Signal value will be h 1 2 = = 0.5..(19) At node 3 the signal value will be from Eq(18and 5) = 1.5 = = = At node 4 the signal value will be from Eq (19 and 5) = 0.5 = = = At node 5 the signal value will be from Eq 20, Eq 21 and Eq 8 = = From Eq(22) and Eq(10) the value of output for the third case i.e. x1=0 and x2=1 will be = =1, h h > CASE 4:- When x1=0 and x2=1, At node 1 value of signal will be = h 1 2 = = 0.5 (24) At node 2 Signal value will be , h 1 2 = = 0.5..(25) At node 3 the signal value will be from Eq(24and 5) = 0.5 = = = At node 4 the signal value will be from Eq (25 and 5) = 0.5 = = = At node 5 the signal value will be from Eq 26, Eq 27 and Eq 8 = = From Eq 28 and Eq 10 the value of the output y for input x1=1 and x2=1 will be = =0, h h < VIII.CONCLUSION From Eq. (11), Eq. (17), Eq. (23) and Eq. (29) it is concluded that the solution proposed proves that it is possible to solve XOR problem using minimum configuration Multilayer Perceptron. MLP provides very nice framework for solving problems that are specifying a non linearly separable domain. Hyperbolic function could be utilized as an activation function for training in the MLP. Hyperbolic tangent function which is a non linear function is utilized as an activation function for squashing the induced local field value or activation value produced after summation to produce output. By inclusion of hidden layer it was possible to solve problem which was complex.

10 One Solution to XOR problem using Multilayer Perceptron having Minimum Configuration REFERENCE [1] Y.S. Abu-Mostafa and J.M. St. Jacques, Information capacity of the Hopfield model, IEEE Transactions on Information Theory, vol. IT- 31, pp , [2] S. Amari, Mathematical foundations of neurocomputing, Proceeding of IEEE, vol. 78, pp , [3] H. Akaike, A new look at the statistical model identification, IEEE Transactions on Automatic Control, vol AC-19, pp , [4] A.F. Atiya and Y.S. Abu-Mostafa, An analog feedback associative memory, IEEE Transactions on Neural Networks, vol. 4, pp , [5] A.R. Barron, Universal approximation bounds for superpositions of a sigmoidal function, IEEE Transactions on Information Theory, vol. 39, pp , [6] J. Bruck, On the convergence properties of the Hopfield model, Proceedings of the IEEE, vol. 78, pp , [7] W.J. Freeman, Why neural networks don t yet fly: Inquiry into the neurodynamics of biological intelligence, IEEE International Conference on Neural Networks, vol. II, pp. 1-7, San Diego, CA, [8] M. Gori and A. Tesi, On the problem of local minima in backpropagation, IEEE Transaction Pattern Analysis and Machine Intellifgence, vol. 14, pp , [9] C.L. Giles, D. Chen, G.Z. Sun, H.H. Chen, Y.C. Lee and M.W. Goudreau, Constructive learning of recurrent neural networks: Limitations of recurrent cascade correlation with a simple solution, IEEE Transactions on Neural Networks, vol. 6, pp , [10] J.F. Cardoso and B. Laheld, Equivariant adaptive source separation, IEEE Transactions on Signal Processing, vol. 44, pp , [11] L.A. Feldkamp and G.V. Puskorius, A signal processing framework based on dynamic neural network with application to problems in adaptation, filtering and classification, Proceeding of the IEEE, vol. 86, 1998.

Neural Networks. Neural network is a network or circuit of neurons. Neurons can be. Biological neurons Artificial neurons

Neural Networks. Neural network is a network or circuit of neurons. Neurons can be. Biological neurons Artificial neurons Neural Networks Neural network is a network or circuit of neurons Neurons can be Biological neurons Artificial neurons Biological neurons Building block of the brain Human brain contains over 10 billion

More information

NEURAL NETWORKS A Comprehensive Foundation

NEURAL NETWORKS A Comprehensive Foundation NEURAL NETWORKS A Comprehensive Foundation Second Edition Simon Haykin McMaster University Hamilton, Ontario, Canada Prentice Hall Prentice Hall Upper Saddle River; New Jersey 07458 Preface xii Acknowledgments

More information

Neural networks. Chapter 20, Section 5 1

Neural networks. Chapter 20, Section 5 1 Neural networks Chapter 20, Section 5 Chapter 20, Section 5 Outline Brains Neural networks Perceptrons Multilayer perceptrons Applications of neural networks Chapter 20, Section 5 2 Brains 0 neurons of

More information

NEURAL NETWORK FUNDAMENTALS WITH GRAPHS, ALGORITHMS, AND APPLICATIONS

NEURAL NETWORK FUNDAMENTALS WITH GRAPHS, ALGORITHMS, AND APPLICATIONS NEURAL NETWORK FUNDAMENTALS WITH GRAPHS, ALGORITHMS, AND APPLICATIONS N. K. Bose HRB-Systems Professor of Electrical Engineering The Pennsylvania State University, University Park P. Liang Associate Professor

More information

Neural Networks and Support Vector Machines

Neural Networks and Support Vector Machines INF5390 - Kunstig intelligens Neural Networks and Support Vector Machines Roar Fjellheim INF5390-13 Neural Networks and SVM 1 Outline Neural networks Perceptrons Neural networks Support vector machines

More information

Introduction to Machine Learning and Data Mining. Prof. Dr. Igor Trajkovski trajkovski@nyus.edu.mk

Introduction to Machine Learning and Data Mining. Prof. Dr. Igor Trajkovski trajkovski@nyus.edu.mk Introduction to Machine Learning and Data Mining Prof. Dr. Igor Trakovski trakovski@nyus.edu.mk Neural Networks 2 Neural Networks Analogy to biological neural systems, the most robust learning systems

More information

Feed-Forward mapping networks KAIST 바이오및뇌공학과 정재승

Feed-Forward mapping networks KAIST 바이오및뇌공학과 정재승 Feed-Forward mapping networks KAIST 바이오및뇌공학과 정재승 How much energy do we need for brain functions? Information processing: Trade-off between energy consumption and wiring cost Trade-off between energy consumption

More information

Lecture 1: Introduction to Neural Networks Kevin Swingler / Bruce Graham

Lecture 1: Introduction to Neural Networks Kevin Swingler / Bruce Graham Lecture 1: Introduction to Neural Networks Kevin Swingler / Bruce Graham kms@cs.stir.ac.uk 1 What are Neural Networks? Neural Networks are networks of neurons, for example, as found in real (i.e. biological)

More information

Role of Neural network in data mining

Role of Neural network in data mining Role of Neural network in data mining Chitranjanjit kaur Associate Prof Guru Nanak College, Sukhchainana Phagwara,(GNDU) Punjab, India Pooja kapoor Associate Prof Swami Sarvanand Group Of Institutes Dinanagar(PTU)

More information

A TUTORIAL. BY: Negin Yousefpour PhD Student Civil Engineering Department TEXAS A&M UNIVERSITY

A TUTORIAL. BY: Negin Yousefpour PhD Student Civil Engineering Department TEXAS A&M UNIVERSITY ARTIFICIAL NEURAL NETWORKS: A TUTORIAL BY: Negin Yousefpour PhD Student Civil Engineering Department TEXAS A&M UNIVERSITY Contents Introduction Origin Of Neural Network Biological Neural Networks ANN Overview

More information

Artificial Neural Networks and Support Vector Machines. CS 486/686: Introduction to Artificial Intelligence

Artificial Neural Networks and Support Vector Machines. CS 486/686: Introduction to Artificial Intelligence Artificial Neural Networks and Support Vector Machines CS 486/686: Introduction to Artificial Intelligence 1 Outline What is a Neural Network? - Perceptron learners - Multi-layer networks What is a Support

More information

An Introduction to Neural Networks

An Introduction to Neural Networks An Introduction to Vincent Cheung Kevin Cannons Signal & Data Compression Laboratory Electrical & Computer Engineering University of Manitoba Winnipeg, Manitoba, Canada Advisor: Dr. W. Kinsner May 27,

More information

Artificial Neural Computation Systems

Artificial Neural Computation Systems Artificial Neural Computation Systems Spring 2003 Technical University of Szczecin Department of Electrical Engineering Lecturer: Prof. Adam Krzyzak,PS 5. Lecture 15.03.2003 147 1. Multilayer Perceptrons............

More information

CONNECTIONIST THEORIES OF LEARNING

CONNECTIONIST THEORIES OF LEARNING CONNECTIONIST THEORIES OF LEARNING Themis N. Karaminis, Michael S.C. Thomas Department of Psychological Sciences, Birkbeck College, University of London London, WC1E 7HX UK tkaram01@students.bbk.ac.uk,

More information

Stock Prediction using Artificial Neural Networks

Stock Prediction using Artificial Neural Networks Stock Prediction using Artificial Neural Networks Abhishek Kar (Y8021), Dept. of Computer Science and Engineering, IIT Kanpur Abstract In this work we present an Artificial Neural Network approach to predict

More information

Lecture 6. Artificial Neural Networks

Lecture 6. Artificial Neural Networks Lecture 6 Artificial Neural Networks 1 1 Artificial Neural Networks In this note we provide an overview of the key concepts that have led to the emergence of Artificial Neural Networks as a major paradigm

More information

Recurrent Neural Networks

Recurrent Neural Networks Recurrent Neural Networks Neural Computation : Lecture 12 John A. Bullinaria, 2015 1. Recurrent Neural Network Architectures 2. State Space Models and Dynamical Systems 3. Backpropagation Through Time

More information

Neural Network Design in Cloud Computing

Neural Network Design in Cloud Computing International Journal of Computer Trends and Technology- volume4issue2-2013 ABSTRACT: Neural Network Design in Cloud Computing B.Rajkumar #1,T.Gopikiran #2,S.Satyanarayana *3 #1,#2Department of Computer

More information

Comparison of Supervised and Unsupervised Learning Classifiers for Travel Recommendations

Comparison of Supervised and Unsupervised Learning Classifiers for Travel Recommendations Volume 3, No. 8, August 2012 Journal of Global Research in Computer Science REVIEW ARTICLE Available Online at www.jgrcs.info Comparison of Supervised and Unsupervised Learning Classifiers for Travel Recommendations

More information

Introduction to Artificial Neural Networks MAE-491/591

Introduction to Artificial Neural Networks MAE-491/591 Introduction to Artificial Neural Networks MAE-491/591 Artificial Neural Networks: Biological Inspiration The brain has been extensively studied by scientists. Vast complexity prevents all but rudimentary

More information

Learning. Artificial Intelligence. Learning. Types of Learning. Inductive Learning Method. Inductive Learning. Learning.

Learning. Artificial Intelligence. Learning. Types of Learning. Inductive Learning Method. Inductive Learning. Learning. Learning Learning is essential for unknown environments, i.e., when designer lacks omniscience Artificial Intelligence Learning Chapter 8 Learning is useful as a system construction method, i.e., expose

More information

INTRODUCTION TO NEURAL NETWORKS

INTRODUCTION TO NEURAL NETWORKS INTRODUCTION TO NEURAL NETWORKS Pictures are taken from http://www.cs.cmu.edu/~tom/mlbook-chapter-slides.html http://research.microsoft.com/~cmbishop/prml/index.htm By Nobel Khandaker Neural Networks An

More information

Method of Combining the Degrees of Similarity in Handwritten Signature Authentication Using Neural Networks

Method of Combining the Degrees of Similarity in Handwritten Signature Authentication Using Neural Networks Method of Combining the Degrees of Similarity in Handwritten Signature Authentication Using Neural Networks Ph. D. Student, Eng. Eusebiu Marcu Abstract This paper introduces a new method of combining the

More information

Introduction to Artificial Neural Networks

Introduction to Artificial Neural Networks POLYTECHNIC UNIVERSITY Department of Computer and Information Science Introduction to Artificial Neural Networks K. Ming Leung Abstract: A computing paradigm known as artificial neural network is introduced.

More information

An Introduction to Artificial Neural Networks (ANN) - Methods, Abstraction, and Usage

An Introduction to Artificial Neural Networks (ANN) - Methods, Abstraction, and Usage An Introduction to Artificial Neural Networks (ANN) - Methods, Abstraction, and Usage Introduction An artificial neural network (ANN) reflects a system that is based on operations of biological neural

More information

6.2.8 Neural networks for data mining

6.2.8 Neural networks for data mining 6.2.8 Neural networks for data mining Walter Kosters 1 In many application areas neural networks are known to be valuable tools. This also holds for data mining. In this chapter we discuss the use of neural

More information

Rate-based artificial neural networks and error backpropagation learning. Scott Murdison Machine learning journal club May 16, 2016

Rate-based artificial neural networks and error backpropagation learning. Scott Murdison Machine learning journal club May 16, 2016 Rate-based artificial neural networks and error backpropagation learning Scott Murdison Machine learning journal club May 16, 2016 Murdison, Leclercq, Lefèvre and Blohm J Neurophys 2015 Neural networks???

More information

CHAPTER 6 NEURAL NETWORK BASED SURFACE ROUGHNESS ESTIMATION

CHAPTER 6 NEURAL NETWORK BASED SURFACE ROUGHNESS ESTIMATION CHAPTER 6 NEURAL NETWORK BASED SURFACE ROUGHNESS ESTIMATION 6.1. KNOWLEDGE REPRESENTATION The function of any representation scheme is to capture the essential features of a problem domain and make that

More information

Neural Nets. General Model Building

Neural Nets. General Model Building Neural Nets To give you an idea of how new this material is, let s do a little history lesson. The origins are typically dated back to the early 1940 s and work by two physiologists, McCulloch and Pitts.

More information

Building MLP networks by construction

Building MLP networks by construction University of Wollongong Research Online Faculty of Informatics - Papers (Archive) Faculty of Engineering and Information Sciences 2000 Building MLP networks by construction Ah Chung Tsoi University of

More information

1 SELF-ORGANIZATION MECHANISM IN THE NETWORKS

1 SELF-ORGANIZATION MECHANISM IN THE NETWORKS Mathematical literature reveals that the number of neural network structures, concepts, methods, and their applications have been well known in neural modeling literature for sometime. It started with

More information

PMR5406 Redes Neurais e Lógica Fuzzy Aula 3 Multilayer Percetrons

PMR5406 Redes Neurais e Lógica Fuzzy Aula 3 Multilayer Percetrons PMR5406 Redes Neurais e Aula 3 Multilayer Percetrons Baseado em: Neural Networks, Simon Haykin, Prentice-Hall, 2 nd edition Slides do curso por Elena Marchiori, Vrie Unviersity Multilayer Perceptrons Architecture

More information

AN APPLICATION OF TIME SERIES ANALYSIS FOR WEATHER FORECASTING

AN APPLICATION OF TIME SERIES ANALYSIS FOR WEATHER FORECASTING AN APPLICATION OF TIME SERIES ANALYSIS FOR WEATHER FORECASTING Abhishek Agrawal*, Vikas Kumar** 1,Ashish Pandey** 2,Imran Khan** 3 *(M. Tech Scholar, Department of Computer Science, Bhagwant University,

More information

A Time Series ANN Approach for Weather Forecasting

A Time Series ANN Approach for Weather Forecasting A Time Series ANN Approach for Weather Forecasting Neeraj Kumar 1, Govind Kumar Jha 2 1 Associate Professor and Head Deptt. Of Computer Science,Nalanda College Of Engineering Chandi(Bihar) 2 Assistant

More information

Feedforward Neural Networks and Backpropagation

Feedforward Neural Networks and Backpropagation Feedforward Neural Networks and Backpropagation Feedforward neural networks Architectural issues, computational capabilities Sigmoidal and radial basis functions Gradient-based learning and Backprogation

More information

Forecasting Demand in the Clothing Industry. Eduardo Miguel Rodrigues 1, Manuel Carlos Figueiredo 2 2

Forecasting Demand in the Clothing Industry. Eduardo Miguel Rodrigues 1, Manuel Carlos Figueiredo 2 2 XI Congreso Galego de Estatística e Investigación de Operacións A Coruña, 24-25-26 de outubro de 2013 Forecasting Demand in the Clothing Industry Eduardo Miguel Rodrigues 1, Manuel Carlos Figueiredo 2

More information

Neural Network Architectures

Neural Network Architectures 6 Neural Network Architectures Bogdan M. Wilamowski Auburn University 6. Introduction... 6-6. Special Easy-to-Train Neural Network Architectures... 6- Polynomial Networks Functional Link Networks Sarajedini

More information

Neural network software tool development: exploring programming language options

Neural network software tool development: exploring programming language options INEB- PSI Technical Report 2006-1 Neural network software tool development: exploring programming language options Alexandra Oliveira aao@fe.up.pt Supervisor: Professor Joaquim Marques de Sá June 2006

More information

EFFICIENT DATA PRE-PROCESSING FOR DATA MINING

EFFICIENT DATA PRE-PROCESSING FOR DATA MINING EFFICIENT DATA PRE-PROCESSING FOR DATA MINING USING NEURAL NETWORKS JothiKumar.R 1, Sivabalan.R.V 2 1 Research scholar, Noorul Islam University, Nagercoil, India Assistant Professor, Adhiparasakthi College

More information

Performance Evaluation of Artificial Neural. Networks for Spatial Data Analysis

Performance Evaluation of Artificial Neural. Networks for Spatial Data Analysis Contemporary Engineering Sciences, Vol. 4, 2011, no. 4, 149-163 Performance Evaluation of Artificial Neural Networks for Spatial Data Analysis Akram A. Moustafa Department of Computer Science Al al-bayt

More information

Open Access Research on Application of Neural Network in Computer Network Security Evaluation. Shujuan Jin *

Open Access Research on Application of Neural Network in Computer Network Security Evaluation. Shujuan Jin * Send Orders for Reprints to reprints@benthamscience.ae 766 The Open Electrical & Electronic Engineering Journal, 2014, 8, 766-771 Open Access Research on Application of Neural Network in Computer Network

More information

ARTIFICIAL NEURAL NETWORKS FOR DATA MINING

ARTIFICIAL NEURAL NETWORKS FOR DATA MINING ARTIFICIAL NEURAL NETWORKS FOR DATA MINING Amrender Kumar I.A.S.R.I., Library Avenue, Pusa, New Delhi-110 012 akha@iasri.res.in 1. Introduction Neural networks, more accurately called Artificial Neural

More information

An Artificial Neural Networks-Based on-line Monitoring Odor Sensing System

An Artificial Neural Networks-Based on-line Monitoring Odor Sensing System Journal of Computer Science 5 (11): 878-882, 2009 ISSN 1549-3636 2009 Science Publications An Artificial Neural Networks-Based on-line Monitoring Odor Sensing System Yousif Al-Bastaki The College of Information

More information

129: Artificial Neural Networks. Ajith Abraham Oklahoma State University, Stillwater, OK, USA 1 INTRODUCTION TO ARTIFICIAL NEURAL NETWORKS

129: Artificial Neural Networks. Ajith Abraham Oklahoma State University, Stillwater, OK, USA 1 INTRODUCTION TO ARTIFICIAL NEURAL NETWORKS 129: Artificial Neural Networks Ajith Abraham Oklahoma State University, Stillwater, OK, USA 1 Introduction to Artificial Neural Networks 901 2 Neural Network Architectures 902 3 Neural Network Learning

More information

Machine Learning and Data Mining -

Machine Learning and Data Mining - Machine Learning and Data Mining - Perceptron Neural Networks Nuno Cavalheiro Marques (nmm@di.fct.unl.pt) Spring Semester 2010/2011 MSc in Computer Science Multi Layer Perceptron Neurons and the Perceptron

More information

Neural Networks. Introduction to Artificial Intelligence CSE 150 May 29, 2007

Neural Networks. Introduction to Artificial Intelligence CSE 150 May 29, 2007 Neural Networks Introduction to Artificial Intelligence CSE 150 May 29, 2007 Administration Last programming assignment has been posted! Final Exam: Tuesday, June 12, 11:30-2:30 Last Lecture Naïve Bayes

More information

Keywords: Image complexity, PSNR, Levenberg-Marquardt, Multi-layer neural network.

Keywords: Image complexity, PSNR, Levenberg-Marquardt, Multi-layer neural network. Global Journal of Computer Science and Technology Volume 11 Issue 3 Version 1.0 Type: Double Blind Peer Reviewed International Research Journal Publisher: Global Journals Inc. (USA) Online ISSN: 0975-4172

More information

SEMINAR OUTLINE. Introduction to Data Mining Using Artificial Neural Networks. Definitions of Neural Networks. Definitions of Neural Networks

SEMINAR OUTLINE. Introduction to Data Mining Using Artificial Neural Networks. Definitions of Neural Networks. Definitions of Neural Networks SEMINAR OUTLINE Introduction to Data Mining Using Artificial Neural Networks ISM 611 Dr. Hamid Nemati Introduction to and Characteristics of Neural Networks Comparison of Neural Networks to traditional

More information

Chapter 4: Artificial Neural Networks

Chapter 4: Artificial Neural Networks Chapter 4: Artificial Neural Networks CS 536: Machine Learning Littman (Wu, TA) Administration icml-03: instructional Conference on Machine Learning http://www.cs.rutgers.edu/~mlittman/courses/ml03/icml03/

More information

A Simple Feature Extraction Technique of a Pattern By Hopfield Network

A Simple Feature Extraction Technique of a Pattern By Hopfield Network A Simple Feature Extraction Technique of a Pattern By Hopfield Network A.Nag!, S. Biswas *, D. Sarkar *, P.P. Sarkar *, B. Gupta **! Academy of Technology, Hoogly - 722 *USIC, University of Kalyani, Kalyani

More information

NEURAL NETWORKS IN DATA MINING

NEURAL NETWORKS IN DATA MINING NEURAL NETWORKS IN DATA MINING 1 DR. YASHPAL SINGH, 2 ALOK SINGH CHAUHAN 1 Reader, Bundelkhand Institute of Engineering & Technology, Jhansi, India 2 Lecturer, United Institute of Management, Allahabad,

More information

Using Neural Networks for Pattern Classification Problems

Using Neural Networks for Pattern Classification Problems Using Neural Networks for Pattern Classification Problems Converting an Image Camera captures an image Image needs to be converted to a form that can be processed by the Neural Network Converting an Image

More information

Comparison of Supervised and Unsupervised Learning Algorithms for Pattern Classification

Comparison of Supervised and Unsupervised Learning Algorithms for Pattern Classification Comparison of Supervised and Unsupervised Learning Algorithms for Pattern Classification R. Sathya Professor, Dept. of MCA, Jyoti Nivas College (Autonomous), Professor and Head, Dept. of Mathematics, Bangalore,

More information

Back Propagation Neural Network for Wireless Networking

Back Propagation Neural Network for Wireless Networking International Journal of Computer Sciences and Engineering Open Access Review Paper Volume-4, Issue-4 E-ISSN: 2347-2693 Back Propagation Neural Network for Wireless Networking Menal Dahiya Maharaja Surajmal

More information

Neural Networks in Data Mining

Neural Networks in Data Mining IOSR Journal of Engineering (IOSRJEN) ISSN (e): 2250-3021, ISSN (p): 2278-8719 Vol. 04, Issue 03 (March. 2014), V6 PP 01-06 www.iosrjen.org Neural Networks in Data Mining Ripundeep Singh Gill, Ashima Department

More information

Electroencephalography Analysis Using Neural Network and Support Vector Machine during Sleep

Electroencephalography Analysis Using Neural Network and Support Vector Machine during Sleep Engineering, 23, 5, 88-92 doi:.4236/eng.23.55b8 Published Online May 23 (http://www.scirp.org/journal/eng) Electroencephalography Analysis Using Neural Network and Support Vector Machine during Sleep JeeEun

More information

FORECASTING THE JORDANIAN STOCK PRICES USING ARTIFICIAL NEURAL NETWORK

FORECASTING THE JORDANIAN STOCK PRICES USING ARTIFICIAL NEURAL NETWORK 1 FORECASTING THE JORDANIAN STOCK PRICES USING ARTIFICIAL NEURAL NETWORK AYMAN A. ABU HAMMAD Civil Engineering Department Applied Science University P. O. Box: 926296, Amman 11931 Jordan SOUMA M. ALHAJ

More information

Neural Networks and Back Propagation Algorithm

Neural Networks and Back Propagation Algorithm Neural Networks and Back Propagation Algorithm Mirza Cilimkovic Institute of Technology Blanchardstown Blanchardstown Road North Dublin 15 Ireland mirzac@gmail.com Abstract Neural Networks (NN) are important

More information

American International Journal of Research in Science, Technology, Engineering & Mathematics

American International Journal of Research in Science, Technology, Engineering & Mathematics American International Journal of Research in Science, Technology, Engineering & Mathematics Available online at http://www.iasir.net ISSN (Print): 2328-349, ISSN (Online): 2328-3580, ISSN (CD-ROM): 2328-3629

More information

Solving Nonlinear Equations Using Recurrent Neural Networks

Solving Nonlinear Equations Using Recurrent Neural Networks Solving Nonlinear Equations Using Recurrent Neural Networks Karl Mathia and Richard Saeks, Ph.D. Accurate Automation Corporation 71 Shallowford Road Chattanooga, Tennessee 37421 Abstract A class of recurrent

More information

Introduction to Neural Networks : Revision Lectures

Introduction to Neural Networks : Revision Lectures Introduction to Neural Networks : Revision Lectures John A. Bullinaria, 2004 1. Module Aims and Learning Outcomes 2. Biological and Artificial Neural Networks 3. Training Methods for Multi Layer Perceptrons

More information

Novelty Detection in image recognition using IRF Neural Networks properties

Novelty Detection in image recognition using IRF Neural Networks properties Novelty Detection in image recognition using IRF Neural Networks properties Philippe Smagghe, Jean-Luc Buessler, Jean-Philippe Urban Université de Haute-Alsace MIPS 4, rue des Frères Lumière, 68093 Mulhouse,

More information

3 An Illustrative Example

3 An Illustrative Example Objectives An Illustrative Example Objectives - Theory and Examples -2 Problem Statement -2 Perceptron - Two-Input Case -4 Pattern Recognition Example -5 Hamming Network -8 Feedforward Layer -8 Recurrent

More information

International Journal of Electronics and Computer Science Engineering 1449

International Journal of Electronics and Computer Science Engineering 1449 International Journal of Electronics and Computer Science Engineering 1449 Available Online at www.ijecse.org ISSN- 2277-1956 Neural Networks in Data Mining Priyanka Gaur Department of Information and

More information

Biological Neurons and Neural Networks, Artificial Neurons

Biological Neurons and Neural Networks, Artificial Neurons Biological Neurons and Neural Networks, Artificial Neurons Neural Computation : Lecture 2 John A. Bullinaria, 2015 1. Organization of the Nervous System and Brain 2. Brains versus Computers: Some Numbers

More information

Comparison of K-means and Backpropagation Data Mining Algorithms

Comparison of K-means and Backpropagation Data Mining Algorithms Comparison of K-means and Backpropagation Data Mining Algorithms Nitu Mathuriya, Dr. Ashish Bansal Abstract Data mining has got more and more mature as a field of basic research in computer science and

More information

Analecta Vol. 8, No. 2 ISSN 2064-7964

Analecta Vol. 8, No. 2 ISSN 2064-7964 EXPERIMENTAL APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS IN ENGINEERING PROCESSING SYSTEM S. Dadvandipour Institute of Information Engineering, University of Miskolc, Egyetemváros, 3515, Miskolc, Hungary,

More information

SELECTING NEURAL NETWORK ARCHITECTURE FOR INVESTMENT PROFITABILITY PREDICTIONS

SELECTING NEURAL NETWORK ARCHITECTURE FOR INVESTMENT PROFITABILITY PREDICTIONS UDC: 004.8 Original scientific paper SELECTING NEURAL NETWORK ARCHITECTURE FOR INVESTMENT PROFITABILITY PREDICTIONS Tonimir Kišasondi, Alen Lovren i University of Zagreb, Faculty of Organization and Informatics,

More information

Power Prediction Analysis using Artificial Neural Network in MS Excel

Power Prediction Analysis using Artificial Neural Network in MS Excel Power Prediction Analysis using Artificial Neural Network in MS Excel NURHASHINMAH MAHAMAD, MUHAMAD KAMAL B. MOHAMMED AMIN Electronic System Engineering Department Malaysia Japan International Institute

More information

Introduction of the Radial Basis Function (RBF) Networks

Introduction of the Radial Basis Function (RBF) Networks Introduction of the Radial Basis Function (RBF) Networks Adrian G. Bors adrian.bors@cs.york.ac.uk Department of Computer Science University of York York, YO10 5DD, UK Abstract In this paper we provide

More information

Dynamic neural network with adaptive Gauss neuron activation function

Dynamic neural network with adaptive Gauss neuron activation function Dynamic neural network with adaptive Gauss neuron activation function Dubravko Majetic, Danko Brezak, Branko Novakovic & Josip Kasac Abstract: An attempt has been made to establish a nonlinear dynamic

More information

SOFTWARE EFFORT ESTIMATION USING RADIAL BASIS FUNCTION NEURAL NETWORKS Ana Maria Bautista, Angel Castellanos, Tomas San Feliu

SOFTWARE EFFORT ESTIMATION USING RADIAL BASIS FUNCTION NEURAL NETWORKS Ana Maria Bautista, Angel Castellanos, Tomas San Feliu International Journal Information Theories and Applications, Vol. 21, Number 4, 2014 319 SOFTWARE EFFORT ESTIMATION USING RADIAL BASIS FUNCTION NEURAL NETWORKS Ana Maria Bautista, Angel Castellanos, Tomas

More information

Neural Machine Translation by Jointly Learning to Align and Translate

Neural Machine Translation by Jointly Learning to Align and Translate Neural Machine Translation by Jointly Learning to Align and Translate Neural Traduction Automatique par Conjointement Apprentissage Pour Aligner et Traduire Dzmitry Bahdanau KyungHyun Cho Yoshua Bengio

More information

Data quality in Accounting Information Systems

Data quality in Accounting Information Systems Data quality in Accounting Information Systems Comparing Several Data Mining Techniques Erjon Zoto Department of Statistics and Applied Informatics Faculty of Economy, University of Tirana Tirana, Albania

More information

Introduction to Neural Networks

Introduction to Neural Networks Introduction to Neural Networks 2nd Year UG, MSc in Computer Science http://www.cs.bham.ac.uk/~jxb/inn.html Lecturer: Dr. John A. Bullinaria http://www.cs.bham.ac.uk/~jxb John A. Bullinaria, 2004 Module

More information

ANN Based Fault Classifier and Fault Locator for Double Circuit Transmission Line

ANN Based Fault Classifier and Fault Locator for Double Circuit Transmission Line International Journal of Computer Sciences and Engineering Open Access Research Paper Volume-4, Special Issue-2, April 2016 E-ISSN: 2347-2693 ANN Based Fault Classifier and Fault Locator for Double Circuit

More information

Introduction to Neural Computation. Neural Computation

Introduction to Neural Computation. Neural Computation Introduction to Neural Computation Level 4/M Neural Computation Level 3 Website: http://www.cs.bham.ac.uk/~jxb/inc.html Lecturer: Dr. John A. Bullinaria John A. Bullinaria, 2015 Module Administration and

More information

Preface. C++ Neural Networks and Fuzzy Logic:Preface. Table of Contents

Preface. C++ Neural Networks and Fuzzy Logic:Preface. Table of Contents C++ Neural Networks and Fuzzy Logic by Valluru B. Rao MTBooks, IDG Books Worldwide, Inc. ISBN: 1558515526 Pub Date: 06/01/95 Table of Contents Preface The number of models available in neural network literature

More information

6. Feed-forward mapping networks

6. Feed-forward mapping networks 6. Feed-forward mapping networks Fundamentals of Computational Neuroscience, T. P. Trappenberg, 2002. Lecture Notes on Brain and Computation Byoung-Tak Zhang Biointelligence Laboratory School of Computer

More information

Neural Computation - Assignment

Neural Computation - Assignment Neural Computation - Assignment Analysing a Neural Network trained by Backpropagation AA SSt t aa t i iss i t i icc aa l l AA nn aa l lyy l ss i iss i oo f vv aa r i ioo i uu ss l lee l aa r nn i inn gg

More information

Lecture 8 Artificial neural networks: Unsupervised learning

Lecture 8 Artificial neural networks: Unsupervised learning Lecture 8 Artificial neural networks: Unsupervised learning Introduction Hebbian learning Generalised Hebbian learning algorithm Competitive learning Self-organising computational map: Kohonen network

More information

Forecasting of Economic Quantities using Fuzzy Autoregressive Model and Fuzzy Neural Network

Forecasting of Economic Quantities using Fuzzy Autoregressive Model and Fuzzy Neural Network Forecasting of Economic Quantities using Fuzzy Autoregressive Model and Fuzzy Neural Network Dušan Marček 1 Abstract Most models for the time series of stock prices have centered on autoregressive (AR)

More information

Iranian J Env Health Sci Eng, 2004, Vol.1, No.2, pp.51-57. Application of Intelligent System for Water Treatment Plant Operation.

Iranian J Env Health Sci Eng, 2004, Vol.1, No.2, pp.51-57. Application of Intelligent System for Water Treatment Plant Operation. Iranian J Env Health Sci Eng, 2004, Vol.1, No.2, pp.51-57 Application of Intelligent System for Water Treatment Plant Operation *A Mirsepassi Dept. of Environmental Health Engineering, School of Public

More information

Chapter 7. Diagnosis and Prognosis of Breast Cancer using Histopathological Data

Chapter 7. Diagnosis and Prognosis of Breast Cancer using Histopathological Data Chapter 7 Diagnosis and Prognosis of Breast Cancer using Histopathological Data In the previous chapter, a method for classification of mammograms using wavelet analysis and adaptive neuro-fuzzy inference

More information

EVALUATION OF NEURAL NETWORK BASED CLASSIFICATION SYSTEMS FOR CLINICAL CANCER DATA CLASSIFICATION

EVALUATION OF NEURAL NETWORK BASED CLASSIFICATION SYSTEMS FOR CLINICAL CANCER DATA CLASSIFICATION EVALUATION OF NEURAL NETWORK BASED CLASSIFICATION SYSTEMS FOR CLINICAL CANCER DATA CLASSIFICATION K. Mumtaz Vivekanandha Institute of Information and Management Studies, Tiruchengode, India S.A.Sheriff

More information

Chapter 12 Discovering New Knowledge Data Mining

Chapter 12 Discovering New Knowledge Data Mining Chapter 12 Discovering New Knowledge Data Mining Becerra-Fernandez, et al. -- Knowledge Management 1/e -- 2004 Prentice Hall Additional material 2007 Dekai Wu Chapter Objectives Introduce the student to

More information

APPLICATION OF ARTIFICIAL NEURAL NETWORKS USING HIJRI LUNAR TRANSACTION AS EXTRACTED VARIABLES TO PREDICT STOCK TREND DIRECTION

APPLICATION OF ARTIFICIAL NEURAL NETWORKS USING HIJRI LUNAR TRANSACTION AS EXTRACTED VARIABLES TO PREDICT STOCK TREND DIRECTION LJMS 2008, 2 Labuan e-journal of Muamalat and Society, Vol. 2, 2008, pp. 9-16 Labuan e-journal of Muamalat and Society APPLICATION OF ARTIFICIAL NEURAL NETWORKS USING HIJRI LUNAR TRANSACTION AS EXTRACTED

More information

Introduction to Neural Networks for Senior Design

Introduction to Neural Networks for Senior Design Introduction to Neural Networks for Senior Design Intro-1 Neural Networks: The Big Picture Artificial Intelligence Neural Networks Expert Systems Machine Learning not ruleoriented ruleoriented Intro-2

More information

Identification of Non-Classical Boundary Conditions with the Aid of Artificial Neural Networks

Identification of Non-Classical Boundary Conditions with the Aid of Artificial Neural Networks University of Tartu Faculty of Mathematics and Computer Science Institute of Computer Science Information Technology Mairit Vikat Identification of Non-Classical Boundary Conditions with the Aid of Artificial

More information

Introduction to Artificial Neural Networks. Introduction to Artificial Neural Networks

Introduction to Artificial Neural Networks. Introduction to Artificial Neural Networks Introduction to Artificial Neural Networks v.3 August Michel Verleysen Introduction - Introduction to Artificial Neural Networks p Why ANNs? p Biological inspiration p Some examples of problems p Historical

More information

Learning to Process Natural Language in Big Data Environment

Learning to Process Natural Language in Big Data Environment CCF ADL 2015 Nanchang Oct 11, 2015 Learning to Process Natural Language in Big Data Environment Hang Li Noah s Ark Lab Huawei Technologies Part 1: Deep Learning - Present and Future Talk Outline Overview

More information

Artificial neural networks

Artificial neural networks Artificial neural networks Now Neurons Neuron models Perceptron learning Multi-layer perceptrons Backpropagation 2 It all starts with a neuron 3 Some facts about human brain ~ 86 billion neurons ~ 10 15

More information

Bank efficiency evaluation using a neural network-dea method

Bank efficiency evaluation using a neural network-dea method Iranian Journal of Mathematical Sciences and Informatics Vol. 4, No. 2 (2009), pp. 33-48 Bank efficiency evaluation using a neural network-dea method G. Aslani a,s.h.momeni-masuleh,a,a.malek b and F. Ghorbani

More information

Neural Networks algorithms and applications

Neural Networks algorithms and applications Neural Networks algorithms and applications By Fiona Nielsen 4i 12/12-2001 Supervisor: Geert Rasmussen Niels Brock Business College 1 Introduction Neural Networks is a field of Artificial Intelligence

More information

Comparison Between Multilayer Feedforward Neural Networks and a Radial Basis Function Network to Detect and Locate Leaks in Pipelines Transporting Gas

Comparison Between Multilayer Feedforward Neural Networks and a Radial Basis Function Network to Detect and Locate Leaks in Pipelines Transporting Gas A publication of 1375 CHEMICAL ENGINEERINGTRANSACTIONS VOL. 32, 2013 Chief Editors:SauroPierucci, JiříJ. Klemeš Copyright 2013, AIDIC ServiziS.r.l., ISBN 978-88-95608-23-5; ISSN 1974-9791 The Italian Association

More information

Data Mining Using Neural Networks: A Guide for Statisticians

Data Mining Using Neural Networks: A Guide for Statisticians Data Mining Using Neural Networks: A Guide for Statisticians Basilio de Bragança Pereira UFRJ - Universidade Federal do Rio de Janeiro Calyampudi Radhakrishna Rao PSU - Penn State University June 2009

More information

Data Mining. Supervised Methods. Ciro Donalek donalek@astro.caltech.edu. Ay/Bi 199ab: Methods of Computa@onal Sciences hcp://esci101.blogspot.

Data Mining. Supervised Methods. Ciro Donalek donalek@astro.caltech.edu. Ay/Bi 199ab: Methods of Computa@onal Sciences hcp://esci101.blogspot. Data Mining Supervised Methods Ciro Donalek donalek@astro.caltech.edu Supervised Methods Summary Ar@ficial Neural Networks Mul@layer Perceptron Support Vector Machines SoLwares Supervised Models: Supervised

More information

Real-Time Credit-Card Fraud Detection using Artificial Neural Network Tuned by Simulated Annealing Algorithm

Real-Time Credit-Card Fraud Detection using Artificial Neural Network Tuned by Simulated Annealing Algorithm Proc. of Int. Conf. on Recent Trends in Information, Telecommunication and Computing, ITC Real-Time Credit-Card Fraud Detection using Artificial Neural Network Tuned by Simulated Annealing Algorithm Azeem

More information

Neural Networks. CAP5610 Machine Learning Instructor: Guo-Jun Qi

Neural Networks. CAP5610 Machine Learning Instructor: Guo-Jun Qi Neural Networks CAP5610 Machine Learning Instructor: Guo-Jun Qi Recap: linear classifier Logistic regression Maximizing the posterior distribution of class Y conditional on the input vector X Support vector

More information

A Prediction Model for Taiwan Tourism Industry Stock Index

A Prediction Model for Taiwan Tourism Industry Stock Index A Prediction Model for Taiwan Tourism Industry Stock Index ABSTRACT Han-Chen Huang and Fang-Wei Chang Yu Da University of Science and Technology, Taiwan Investors and scholars pay continuous attention

More information