Chapter - 3. ANN Approach for Efficient Computation of Logarithm and Antilogarithm of Decimal Numbers
|
|
- Oswald Gilbert
- 5 years ago
- Views:
Transcription
1 Chapter - 3 ANN Approach for Efficient Computation of Logarithm and Antilogarithm of Decimal Numbers
2 Chapter - 3 ANN Approach for Efficient Computation of Logarithm and Antilogarithm of Decimal Numbers 3.1 Introduction The artificial neurons are inherently associated with nonlinearities. Hence an ANN structure can be conveniently used to model different linear and nonlinear systems. To assess the modeling potentiality o f ANN structure, we have addressed a simple problem o f logarithm and antilogarithm in this chapter. Computation o f logarithm o f a number and its inverse computation are frequently encountered in many applications. The logarithm o f a number x to the base 10 is defined by y a= log io (x) To get back the original number, we have to compute the antilog o f ya which is defined as * = antilogio (y j The objective o f this chapter is to develop a simple neural structure for the computation o f log o f any number and another simple structure to compute the original num ber from its antilog. 3.2 Modeling o f an ANN structure to compute logarithm For developing a logarithmic processor, the Neural Network (NN) is used in an adaptive manner as shown in Fig In this figure x refers to an input number whose log value is to be computed.
3 ya Fig. 3.1 An ANN Scheme The output o f the NN processor computes an estimate o f the log value. In the beginning the parameters o f the neural processor are initialized to some random values. The desired log value o f the input number is known to us which is compared with the estimated value y a. The difference of these two numbers is denoted as the error e. Knowledge o f this error e is used to compute the change in the connecting weights o f the neural model. To completely train the network, a set o f input patterns lying between 1 to 10 is first generated which is used to train the network. Using the standard log table, the log values o f these numbers are also obtained to serve as the desired values w hile training. Since computation o f logarithm is relatively a simple application, we have considered a single layer network to serve as a logarithmic processor. This is shown in Fig Fig. 3,2. Scheme for logjo computation using a single layer, single neuron ANN
4 The input x is weighted by a single weight w and a bias weight Wb to produce the linear output. This linear output is passed through a nonlinear sigmoid function defined in Section o f chapter 2. The estimated output y a is compared with corresponding log value ya to produce error e. Initially this error will be large but as the training o f the weights continues, on the application o f different patterns, mean square error (M SE) obtained from e gradually diminishes to a very small value. The number o f patterns used for training was 80. The procedure for adaptation o f the neural model is known as pattern matching method. Procedure for learning o f this method is outlined in Section o f Chapter 2. The MSE is recorded for each iteration as long as training continues. The relation between MSE and iterations has been plotted and shown in Fig The curve is known as a learning characteristics of the neural model. Each o f the values o f \x and a are set to 0.1 for obtaining the best convergence. The steady state connecting weights w and Wb obtained from simulation are given in Table 3.1. These two weights and the single neuron represent the neural log model which is very simple and can predict the logarithm o f any number lying between 1 to 10. To assess the potentiality o f the simulated log model, various numbers between 1 to 10 were used as input to the model and the computed outputs were compared with the true log values. The test results are presented in Table 3.2. It is observed that the percentage o f error is less than 1.75% in all cases. The accuracy can further be improved by incorporating one more neuron in the second layer or by increasing number o f inputs by functional expansion method. However in these two
5 cases the complexity would increase compared to the accuracy achieved, o, , o c U) co S ' o o o o O o O o o CM CO Iterations Fig. 3.3 Learning Characteristics for log computation Table 3.1 Weights obtained from simulation for log computation a = 0.1, = 0.1 w bias weight \vb Table 3.2 Comparison between simulated and true log results. R andom Decimal N um ber x Desired Result ya Estim ated Result Percentage E rro r y«
6 3.3 Modeling of an ANN structure to compute Antiiogarithm Computation o f antilogarithm is an inverse process which is basically a nonlinear operation. In an antilog processor, the input will be the log o f a number and output will be the original number. Such an inverse processor can be conveniently designed by a neural network. A multilayer ANN structure can be used to model an antilog processor but would involve more complexity and cost as well. In this chapter we have proposed an economical single layer ANN structure using functional expansion as is shown in Fig Fig. 3.4: ANN Schem e for an tilo g y com putation using functional expansion A single input ya which is the logio o f x is functionally expanded to nine values such as y^ cos7iya, co s2 7 ty a,co s8 7 ty a The purpose o f this expansion is to introduce some nonlinearity to the input so that the requirement o f number o f multilayers is reduced to one. These nine points are weighted by a set o f nine random weights and linearly added in the ANN. This sum is added with a bias weight w b and is passed through a nonlinear sigmoid function to produce the estimate o f the desired number as *. Then x is compared with true value x to produce error e. In the
7 beginning the magnitude o f this error is high as the connecting weights are not properly adjusted. To develop the antilog processor, we consider a set o f log values and the original numbers to serve as input and desired output respectively for training the model. Each tim e one value o f ya (logjo(x) ) is applied and the corresponding antilog value x is computed and the magnitude o f the difference between x and x is calculated. The pattern matching o f learning described in Section o f Chapter 2 is used to adapt the nine weights and one bias weight Wb so that the average MSE progressively decreases. The training is continued until the MSE attains the possible minimum value. The selection o f p. and a is very crucial as they control the rate o f convergence as well as minimum MSE. In this simulation, [i = 0.1 and a = 0.7 were used. The learning characteristics for developing the antilog computation model is shown in Fig The steady state MSE is set at around -40 db after about 1500 iterations. When the training is complete, the learning is withdrawn and the final weights achieved correspond to steady state weights o f the antilog neural model. Table 3.3 represents the magnitudes o f the steady state weights obtained from the computer simulation o f the antilog model. Determination o f nine connecting weights and Wb constitute the development o f neural network. To test the efficiency o f this model, random decimal values were generated and their logio values were used as the inputs to predict the desired results x. The results have been compared with the true values o f x and the percentage o f error are computed. These results are shown in Table 3.4. It is observed from the table that percentage o f error is less than 1.75% in each case. This error can further be minimized by increasing the num ber o f functional expansion points at the input.
8 -60 I o o o Iterations Fig. 3.5 Learning Characteristics for antilog computation Table 3.3 Weights obtained from simulation of antilog computation a = 0.1, ^ = 0.7 Wo W l w w W W W w7-0, w bias weight Wb
9 Table 3.4. C om parison between sim ulated an d tru e antilog results log(x) Desired Result y* Estimated Result y a Percentage E rro r Conclusions Since the artificial neuron contains nonlinearity, an A NN structure is quite suitable to model nonlinear systems. Keeping this in view, investigation has been made in this chapter to develop simple ANN model to compute logarithm and antilogarithm values o f decimal numbers. The problem chosen in this chapter is though quite simple, its study reveals the potentiality o f nonlinearity modeling o f neural networks. In both log and antilog computation, single neuron has been used to yield simple structure. In log computation a single weight and a bias weigh have been evaluated by simulation to act as a model for log computation. On testing the efficiency o f this model, it is observed that the percentage o f error lies less than 1.75% which is quite acceptable. The hardware cost o f this method is very cheap. Similarly a functional expansion based antilog model has been developed through simulation. The performance o f this model has been tested by supplying unknown data and the predicted results o f this model are observed to lie between 2% less than the true results. Thus it can be concluded that neural structure is a potential tool for nonlinear modeling which has been verified by developing log and antilog models and testing their perform ance.
10 References [l.jr u m elh art, D.E., H int on, G.E. and W illiam s, R.J. 1986, Learning internal representation by error propagation, in R um elhart, D.E. an d M cclelland, J.L.; (Ems), Parallel Distributed Processing, Cambridge, M.A. FIT Press Chap 8, pp [2.] Jam es A. F reem an and D avid M. S kapura, Neural Networks, Algorithms, Applications, and Programming Technique, Addison Wesley Publishing Company, [3.JY. Pao,Adaptive Pattern Recognition and Neural Networks, Reading, M.A. : Addison W esley Publishers, [4.]G.Panda and A.K.Saxena, An Effecient Data Communication Scheme using Artificial Neural Network, pp proceeding o f COMNET-94 at Patna. [5.]G.Panda,R.K.Singh and A.K.Saxena, Artificial Neural Network Approach for Efficient Computation o f Logarithm and Antilogarithm o f Decimal Numbers, pp 69-73, proceeding o f COM NET-97 at Patna.
Neural Network Identification of Non Linear Systems Using State Space Techniques.
Neural Network Identification of Non Linear Systems Using State Space Techniques. Joan Codina, J. Carlos Aguado, Josep M. Fuertes. Automatic Control and Computer Engineering Department Universitat Politècnica
More informationNeural Networks and the Back-propagation Algorithm
Neural Networks and the Back-propagation Algorithm Francisco S. Melo In these notes, we provide a brief overview of the main concepts concerning neural networks and the back-propagation algorithm. We closely
More informationSimple neuron model Components of simple neuron
Outline 1. Simple neuron model 2. Components of artificial neural networks 3. Common activation functions 4. MATLAB representation of neural network. Single neuron model Simple neuron model Components
More informationNeural Networks. Nicholas Ruozzi University of Texas at Dallas
Neural Networks Nicholas Ruozzi University of Texas at Dallas Handwritten Digit Recognition Given a collection of handwritten digits and their corresponding labels, we d like to be able to correctly classify
More informationA Logarithmic Neural Network Architecture for Unbounded Non-Linear Function Approximation
1 Introduction A Logarithmic Neural Network Architecture for Unbounded Non-Linear Function Approximation J Wesley Hines Nuclear Engineering Department The University of Tennessee Knoxville, Tennessee,
More informationARTIFICIAL NEURAL NETWORK PART I HANIEH BORHANAZAD
ARTIFICIAL NEURAL NETWORK PART I HANIEH BORHANAZAD WHAT IS A NEURAL NETWORK? The simplest definition of a neural network, more properly referred to as an 'artificial' neural network (ANN), is provided
More informationAddress for Correspondence
Research Article APPLICATION OF ARTIFICIAL NEURAL NETWORK FOR INTERFERENCE STUDIES OF LOW-RISE BUILDINGS 1 Narayan K*, 2 Gairola A Address for Correspondence 1 Associate Professor, Department of Civil
More informationArtificial Neural Networks
Introduction ANN in Action Final Observations Application: Poverty Detection Artificial Neural Networks Alvaro J. Riascos Villegas University of los Andes and Quantil July 6 2018 Artificial Neural Networks
More informationMultilayer Perceptron
Outline Hong Chang Institute of Computing Technology, Chinese Academy of Sciences Machine Learning Methods (Fall 2012) Outline Outline I 1 Introduction 2 Single Perceptron 3 Boolean Function Learning 4
More informationInstruction Sheet for SOFT COMPUTING LABORATORY (EE 753/1)
Instruction Sheet for SOFT COMPUTING LABORATORY (EE 753/1) Develop the following programs in the MATLAB environment: 1. Write a program in MATLAB for Feed Forward Neural Network with Back propagation training
More informationIntroduction Neural Networks - Architecture Network Training Small Example - ZIP Codes Summary. Neural Networks - I. Henrik I Christensen
Neural Networks - I Henrik I Christensen Robotics & Intelligent Machines @ GT Georgia Institute of Technology, Atlanta, GA 30332-0280 hic@cc.gatech.edu Henrik I Christensen (RIM@GT) Neural Networks 1 /
More informationArtificial Neural Network
Artificial Neural Network Contents 2 What is ANN? Biological Neuron Structure of Neuron Types of Neuron Models of Neuron Analogy with human NN Perceptron OCR Multilayer Neural Network Back propagation
More informationMultilayer Perceptron Tutorial
Multilayer Perceptron Tutorial Leonardo Noriega School of Computing Staffordshire University Beaconside Staffordshire ST18 0DG email: l.a.noriega@staffs.ac.uk November 17, 2005 1 Introduction to Neural
More informationKeywords- Source coding, Huffman encoding, Artificial neural network, Multilayer perceptron, Backpropagation algorithm
Volume 4, Issue 5, May 2014 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Huffman Encoding
More informationArtificial neural networks
Artificial neural networks Chapter 8, Section 7 Artificial Intelligence, spring 203, Peter Ljunglöf; based on AIMA Slides c Stuart Russel and Peter Norvig, 2004 Chapter 8, Section 7 Outline Brains Neural
More informationNeural networks. Chapter 19, Sections 1 5 1
Neural networks Chapter 19, Sections 1 5 Chapter 19, Sections 1 5 1 Outline Brains Neural networks Perceptrons Multilayer perceptrons Applications of neural networks Chapter 19, Sections 1 5 2 Brains 10
More informationNeural Networks Introduction
Neural Networks Introduction H.A Talebi Farzaneh Abdollahi Department of Electrical Engineering Amirkabir University of Technology Winter 2011 H. A. Talebi, Farzaneh Abdollahi Neural Networks 1/22 Biological
More informationNeural Networks for Protein Structure Prediction Brown, JMB CS 466 Saurabh Sinha
Neural Networks for Protein Structure Prediction Brown, JMB 1999 CS 466 Saurabh Sinha Outline Goal is to predict secondary structure of a protein from its sequence Artificial Neural Network used for this
More informationCSE 352 (AI) LECTURE NOTES Professor Anita Wasilewska. NEURAL NETWORKS Learning
CSE 352 (AI) LECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS Learning Neural Networks Classifier Short Presentation INPUT: classification data, i.e. it contains an classification (class) attribute.
More informationEEE 241: Linear Systems
EEE 4: Linear Systems Summary # 3: Introduction to artificial neural networks DISTRIBUTED REPRESENTATION An ANN consists of simple processing units communicating with each other. The basic elements of
More informationPulse Shape Analysis
Pulse Shape Analysis Fabiana Cossavella Max-Planck Institut für Physik, München 26 March 2011 OUTLINE: motivation description of the procedure results Fabiana Cossavella Pulse Shape Analysis 1/11 Motivation:
More informationA Feature Based Neural Network Model for Weather Forecasting
World Academy of Science, Engineering and Technology 4 2 A Feature Based Neural Network Model for Weather Forecasting Paras, Sanjay Mathur, Avinash Kumar, and Mahesh Chandra Abstract Weather forecasting
More informationNeural networks. Chapter 20. Chapter 20 1
Neural networks Chapter 20 Chapter 20 1 Outline Brains Neural networks Perceptrons Multilayer networks Applications of neural networks Chapter 20 2 Brains 10 11 neurons of > 20 types, 10 14 synapses, 1ms
More informationArtificial Neural Network : Training
Artificial Neural Networ : Training Debasis Samanta IIT Kharagpur debasis.samanta.iitgp@gmail.com 06.04.2018 Debasis Samanta (IIT Kharagpur) Soft Computing Applications 06.04.2018 1 / 49 Learning of neural
More informationData Mining Part 5. Prediction
Data Mining Part 5. Prediction 5.5. Spring 2010 Instructor: Dr. Masoud Yaghini Outline How the Brain Works Artificial Neural Networks Simple Computing Elements Feed-Forward Networks Perceptrons (Single-layer,
More informationDesign Collocation Neural Network to Solve Singular Perturbed Problems with Initial Conditions
Article International Journal of Modern Engineering Sciences, 204, 3(): 29-38 International Journal of Modern Engineering Sciences Journal homepage:www.modernscientificpress.com/journals/ijmes.aspx ISSN:
More information<Special Topics in VLSI> Learning for Deep Neural Networks (Back-propagation)
Learning for Deep Neural Networks (Back-propagation) Outline Summary of Previous Standford Lecture Universal Approximation Theorem Inference vs Training Gradient Descent Back-Propagation
More informationNeural Networks. Chapter 18, Section 7. TB Artificial Intelligence. Slides from AIMA 1/ 21
Neural Networks Chapter 8, Section 7 TB Artificial Intelligence Slides from AIMA http://aima.cs.berkeley.edu / 2 Outline Brains Neural networks Perceptrons Multilayer perceptrons Applications of neural
More informationUnit 8: Introduction to neural networks. Perceptrons
Unit 8: Introduction to neural networks. Perceptrons D. Balbontín Noval F. J. Martín Mateos J. L. Ruiz Reina A. Riscos Núñez Departamento de Ciencias de la Computación e Inteligencia Artificial Universidad
More informationSimple Neural Nets For Pattern Classification
CHAPTER 2 Simple Neural Nets For Pattern Classification Neural Networks General Discussion One of the simplest tasks that neural nets can be trained to perform is pattern classification. In pattern classification
More informationSerious limitations of (single-layer) perceptrons: Cannot learn non-linearly separable tasks. Cannot approximate (learn) non-linear functions
BACK-PROPAGATION NETWORKS Serious limitations of (single-layer) perceptrons: Cannot learn non-linearly separable tasks Cannot approximate (learn) non-linear functions Difficult (if not impossible) to design
More informationArtifical Neural Networks
Neural Networks Artifical Neural Networks Neural Networks Biological Neural Networks.................................. Artificial Neural Networks................................... 3 ANN Structure...........................................
More informationSTRUCTURED NEURAL NETWORK FOR NONLINEAR DYNAMIC SYSTEMS MODELING
STRUCTURED NEURAL NETWORK FOR NONLINEAR DYNAIC SYSTES ODELING J. CODINA, R. VILLÀ and J.. FUERTES UPC-Facultat d Informàtica de Barcelona, Department of Automatic Control and Computer Engineeering, Pau
More informationArtificial Neural Networks
Artificial Neural Networks Stephan Dreiseitl University of Applied Sciences Upper Austria at Hagenberg Harvard-MIT Division of Health Sciences and Technology HST.951J: Medical Decision Support Knowledge
More informationECE521 Lectures 9 Fully Connected Neural Networks
ECE521 Lectures 9 Fully Connected Neural Networks Outline Multi-class classification Learning multi-layer neural networks 2 Measuring distance in probability space We learnt that the squared L2 distance
More informationLecture 4: Perceptrons and Multilayer Perceptrons
Lecture 4: Perceptrons and Multilayer Perceptrons Cognitive Systems II - Machine Learning SS 2005 Part I: Basic Approaches of Concept Learning Perceptrons, Artificial Neuronal Networks Lecture 4: Perceptrons
More informationApplication of Artificial Neural Networks in Evaluation and Identification of Electrical Loss in Transformers According to the Energy Consumption
Application of Artificial Neural Networks in Evaluation and Identification of Electrical Loss in Transformers According to the Energy Consumption ANDRÉ NUNES DE SOUZA, JOSÉ ALFREDO C. ULSON, IVAN NUNES
More informationEE04 804(B) Soft Computing Ver. 1.2 Class 2. Neural Networks - I Feb 23, Sasidharan Sreedharan
EE04 804(B) Soft Computing Ver. 1.2 Class 2. Neural Networks - I Feb 23, 2012 Sasidharan Sreedharan www.sasidharan.webs.com 3/1/2012 1 Syllabus Artificial Intelligence Systems- Neural Networks, fuzzy logic,
More informationFeature Selection Optimization Solar Insolation Prediction Using Artificial Neural Network: Perspective Bangladesh
American Journal of Engineering Research (AJER) 2016 American Journal of Engineering Research (AJER) e-issn: 2320-0847 p-issn : 2320-0936 Volume-5, Issue-8, pp-261-265 www.ajer.org Research Paper Open
More informationUnit III. A Survey of Neural Network Model
Unit III A Survey of Neural Network Model 1 Single Layer Perceptron Perceptron the first adaptive network architecture was invented by Frank Rosenblatt in 1957. It can be used for the classification of
More informationLECTURE # - NEURAL COMPUTATION, Feb 04, Linear Regression. x 1 θ 1 output... θ M x M. Assumes a functional form
LECTURE # - EURAL COPUTATIO, Feb 4, 4 Linear Regression Assumes a functional form f (, θ) = θ θ θ K θ (Eq) where = (,, ) are the attributes and θ = (θ, θ, θ ) are the function parameters Eample: f (, θ)
More informationArtificial Neural Networks. Historical description
Artificial Neural Networks Historical description Victor G. Lopez 1 / 23 Artificial Neural Networks (ANN) An artificial neural network is a computational model that attempts to emulate the functions of
More informationAI Programming CS F-20 Neural Networks
AI Programming CS662-2008F-20 Neural Networks David Galles Department of Computer Science University of San Francisco 20-0: Symbolic AI Most of this class has been focused on Symbolic AI Focus or symbols
More informationLecture 7 Artificial neural networks: Supervised learning
Lecture 7 Artificial neural networks: Supervised learning Introduction, or how the brain works The neuron as a simple computing element The perceptron Multilayer neural networks Accelerated learning in
More informationCOMS 4771 Introduction to Machine Learning. Nakul Verma
COMS 4771 Introduction to Machine Learning Nakul Verma Announcements HW1 due next lecture Project details are available decide on the group and topic by Thursday Last time Generative vs. Discriminative
More informationArtificial Neural Network Based Approach for Design of RCC Columns
Artificial Neural Network Based Approach for Design of RCC Columns Dr T illai, ember I Karthekeyan, Non-member Recent developments in artificial neural network have opened up new possibilities in the field
More informationCheng Soon Ong & Christian Walder. Canberra February June 2018
Cheng Soon Ong & Christian Walder Research Group and College of Engineering and Computer Science Canberra February June 2018 Outlines Overview Introduction Linear Algebra Probability Linear Regression
More informationNeural Networks Lecturer: J. Matas Authors: J. Matas, B. Flach, O. Drbohlav
Neural Networks 30.11.2015 Lecturer: J. Matas Authors: J. Matas, B. Flach, O. Drbohlav 1 Talk Outline Perceptron Combining neurons to a network Neural network, processing input to an output Learning Cost
More informationStatistical Learning Reading Assignments
Statistical Learning Reading Assignments S. Gong et al. Dynamic Vision: From Images to Face Recognition, Imperial College Press, 2001 (Chapt. 3, hard copy). T. Evgeniou, M. Pontil, and T. Poggio, "Statistical
More informationDETECTING PROCESS STATE CHANGES BY NONLINEAR BLIND SOURCE SEPARATION. Alexandre Iline, Harri Valpola and Erkki Oja
DETECTING PROCESS STATE CHANGES BY NONLINEAR BLIND SOURCE SEPARATION Alexandre Iline, Harri Valpola and Erkki Oja Laboratory of Computer and Information Science Helsinki University of Technology P.O.Box
More informationLast updated: Oct 22, 2012 LINEAR CLASSIFIERS. J. Elder CSE 4404/5327 Introduction to Machine Learning and Pattern Recognition
Last updated: Oct 22, 2012 LINEAR CLASSIFIERS Problems 2 Please do Problem 8.3 in the textbook. We will discuss this in class. Classification: Problem Statement 3 In regression, we are modeling the relationship
More informationTutorial on Tangent Propagation
Tutorial on Tangent Propagation Yichuan Tang Centre for Theoretical Neuroscience February 5, 2009 1 Introduction Tangent Propagation is the name of a learning technique of an artificial neural network
More informationTemperature Prediction based on Artificial Neural Network and its Impact on Rice Production, Case Study: Bangladesh
erature Prediction based on Artificial Neural Network and its Impact on Rice Production, Case Study: Bangladesh Tushar Kanti Routh Lecturer, Department of Electronics & Telecommunication Engineering, South
More informationNeural Networks, Computation Graphs. CMSC 470 Marine Carpuat
Neural Networks, Computation Graphs CMSC 470 Marine Carpuat Binary Classification with a Multi-layer Perceptron φ A = 1 φ site = 1 φ located = 1 φ Maizuru = 1 φ, = 2 φ in = 1 φ Kyoto = 1 φ priest = 0 φ
More informationArtificial Neural Network Method of Rock Mass Blastability Classification
Artificial Neural Network Method of Rock Mass Blastability Classification Jiang Han, Xu Weiya, Xie Shouyi Research Institute of Geotechnical Engineering, Hohai University, Nanjing, Jiangshu, P.R.China
More informationNeural 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 informationUsing Neural Networks for Identification and Control of Systems
Using Neural Networks for Identification and Control of Systems Jhonatam Cordeiro Department of Industrial and Systems Engineering North Carolina A&T State University, Greensboro, NC 27411 jcrodrig@aggies.ncat.edu
More informationk k k 1 Lecture 9: Applying Backpropagation Lecture 9: Applying Backpropagation 3 Lecture 9: Applying Backpropagation
K-Class Classification Problem Let us denote the -th class by C, with n exemplars or training samples, forming the sets T for = 1,, K: {( x, ) p = 1 n } T = d,..., p p The complete training set is T =
More information2015 Todd Neller. A.I.M.A. text figures 1995 Prentice Hall. Used by permission. Neural Networks. Todd W. Neller
2015 Todd Neller. A.I.M.A. text figures 1995 Prentice Hall. Used by permission. Neural Networks Todd W. Neller Machine Learning Learning is such an important part of what we consider "intelligence" that
More informationApplied Statistics. Multivariate Analysis - part II. Troels C. Petersen (NBI) Statistics is merely a quantization of common sense 1
Applied Statistics Multivariate Analysis - part II Troels C. Petersen (NBI) Statistics is merely a quantization of common sense 1 Fisher Discriminant You want to separate two types/classes (A and B) of
More informationArtificial Neural Networks
Artificial Neural Networks 鮑興國 Ph.D. National Taiwan University of Science and Technology Outline Perceptrons Gradient descent Multi-layer networks Backpropagation Hidden layer representations Examples
More informationCSC242: Intro to AI. Lecture 21
CSC242: Intro to AI Lecture 21 Administrivia Project 4 (homeworks 18 & 19) due Mon Apr 16 11:59PM Posters Apr 24 and 26 You need an idea! You need to present it nicely on 2-wide by 4-high landscape pages
More informationInternational Journal of Advanced Research in Computer Science and Software Engineering
Volume 3, Issue 4, April 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Application of
More informationNeural Networks DWML, /25
DWML, 2007 /25 Neural networks: Biological and artificial Consider humans: Neuron switching time 0.00 second Number of neurons 0 0 Connections per neuron 0 4-0 5 Scene recognition time 0. sec 00 inference
More informationRevision: Neural Network
Revision: Neural Network Exercise 1 Tell whether each of the following statements is true or false by checking the appropriate box. Statement True False a) A perceptron is guaranteed to perfectly learn
More informationRESPONSE PREDICTION OF STRUCTURAL SYSTEM SUBJECT TO EARTHQUAKE MOTIONS USING ARTIFICIAL NEURAL NETWORK
ASIAN JOURNAL OF CIVIL ENGINEERING (BUILDING AND HOUSING) VOL. 7, NO. 3 (006) PAGES 301-308 RESPONSE PREDICTION OF STRUCTURAL SYSTEM SUBJECT TO EARTHQUAKE MOTIONS USING ARTIFICIAL NEURAL NETWORK S. Chakraverty
More informationPlan. Perceptron Linear discriminant. Associative memories Hopfield networks Chaotic networks. Multilayer perceptron Backpropagation
Neural Networks Plan Perceptron Linear discriminant Associative memories Hopfield networks Chaotic networks Multilayer perceptron Backpropagation Perceptron Historically, the first neural net Inspired
More informationIntroduction to Natural Computation. Lecture 9. Multilayer Perceptrons and Backpropagation. Peter Lewis
Introduction to Natural Computation Lecture 9 Multilayer Perceptrons and Backpropagation Peter Lewis 1 / 25 Overview of the Lecture Why multilayer perceptrons? Some applications of multilayer perceptrons.
More informationArtificial Neural Network and Fuzzy Logic
Artificial Neural Network and Fuzzy Logic 1 Syllabus 2 Syllabus 3 Books 1. Artificial Neural Networks by B. Yagnanarayan, PHI - (Cover Topologies part of unit 1 and All part of Unit 2) 2. Neural Networks
More informationLogarithms Tutorial for Chemistry Students
1 Logarithms 1.1 What is a logarithm? Logarithms Tutorial for Chemistry Students Logarithms are the mathematical function that is used to represent the number (y) to which a base integer (a) is raised
More informationNeural Networks Application to Reduction of Train Caused Distortions in Magnetotelluric Measurement Data
SCHEAE INFORM ATICAE VOLUM E 17/18 2009 Neural Networs Application to Reduction of Train Caused istortions in Magnetotelluric Measurement ata MARZENA BIELECKA 1, TOMASZ. ANEK 1, MAREK WOJYŁA 2, RZEORZ
More informationApril 9, Depto. de Ing. de Sistemas e Industrial Universidad Nacional de Colombia, Bogotá. Linear Classification Models. Fabio A. González Ph.D.
Depto. de Ing. de Sistemas e Industrial Universidad Nacional de Colombia, Bogotá April 9, 2018 Content 1 2 3 4 Outline 1 2 3 4 problems { C 1, y(x) threshold predict(x) = C 2, y(x) < threshold, with threshold
More informationCS:4420 Artificial Intelligence
CS:4420 Artificial Intelligence Spring 2018 Neural Networks Cesare Tinelli The University of Iowa Copyright 2004 18, Cesare Tinelli and Stuart Russell a a These notes were originally developed by Stuart
More informationArtificial Neural Networks" and Nonparametric Methods" CMPSCI 383 Nov 17, 2011!
Artificial Neural Networks" and Nonparametric Methods" CMPSCI 383 Nov 17, 2011! 1 Todayʼs lecture" How the brain works (!)! Artificial neural networks! Perceptrons! Multilayer feed-forward networks! Error
More informationLinear Least-Squares Based Methods for Neural Networks Learning
Linear Least-Squares Based Methods for Neural Networks Learning Oscar Fontenla-Romero 1, Deniz Erdogmus 2, JC Principe 2, Amparo Alonso-Betanzos 1, and Enrique Castillo 3 1 Laboratory for Research and
More informationAnalysis of Fast Input Selection: Application in Time Series Prediction
Analysis of Fast Input Selection: Application in Time Series Prediction Jarkko Tikka, Amaury Lendasse, and Jaakko Hollmén Helsinki University of Technology, Laboratory of Computer and Information Science,
More informationIntroduction to Neural Networks
Introduction to Neural Networks What are (Artificial) Neural Networks? Models of the brain and nervous system Highly parallel Process information much more like the brain than a serial computer Learning
More informationNeural Networks. Advanced data-mining. Yongdai Kim. Department of Statistics, Seoul National University, South Korea
Neural Networks Advanced data-mining Yongdai Kim Department of Statistics, Seoul National University, South Korea What is Neural Networks? One of supervised learning method using one or more hidden layer.
More information4. Multilayer Perceptrons
4. Multilayer Perceptrons This is a supervised error-correction learning algorithm. 1 4.1 Introduction A multilayer feedforward network consists of an input layer, one or more hidden layers, and an output
More informationA Novel Activity Detection Method
A Novel Activity Detection Method Gismy George P.G. Student, Department of ECE, Ilahia College of,muvattupuzha, Kerala, India ABSTRACT: This paper presents an approach for activity state recognition of
More informationIntroduction to Neural Networks
Introduction to Neural Networks Steve Renals Automatic Speech Recognition ASR Lecture 10 24 February 2014 ASR Lecture 10 Introduction to Neural Networks 1 Neural networks for speech recognition Introduction
More informationNeural Networks in Structured Prediction. November 17, 2015
Neural Networks in Structured Prediction November 17, 2015 HWs and Paper Last homework is going to be posted soon Neural net NER tagging model This is a new structured model Paper - Thursday after Thanksgiving
More informationCSC321 Lecture 4: Learning a Classifier
CSC321 Lecture 4: Learning a Classifier Roger Grosse Roger Grosse CSC321 Lecture 4: Learning a Classifier 1 / 28 Overview Last time: binary classification, perceptron algorithm Limitations of the perceptron
More informationAn artificial neural networks (ANNs) model is a functional abstraction of the
CHAPER 3 3. Introduction An artificial neural networs (ANNs) model is a functional abstraction of the biological neural structures of the central nervous system. hey are composed of many simple and highly
More informationARTIFICIAL INTELLIGENCE. Artificial Neural Networks
INFOB2KI 2017-2018 Utrecht University The Netherlands ARTIFICIAL INTELLIGENCE Artificial Neural Networks Lecturer: Silja Renooij These slides are part of the INFOB2KI Course Notes available from www.cs.uu.nl/docs/vakken/b2ki/schema.html
More informationNeural Networks. Fundamentals Framework for distributed processing Network topologies Training of ANN s Notation Perceptron Back Propagation
Neural Networks Fundamentals Framework for distributed processing Network topologies Training of ANN s Notation Perceptron Back Propagation Neural Networks Historical Perspective A first wave of interest
More informationPart 8: Neural Networks
METU Informatics Institute Min720 Pattern Classification ith Bio-Medical Applications Part 8: Neural Netors - INTRODUCTION: BIOLOGICAL VS. ARTIFICIAL Biological Neural Netors A Neuron: - A nerve cell as
More informationDeep Neural Networks
Deep Neural Networks DT2118 Speech and Speaker Recognition Giampiero Salvi KTH/CSC/TMH giampi@kth.se VT 2015 1 / 45 Outline State-to-Output Probability Model Artificial Neural Networks Perceptron Multi
More informationThe perceptron learning algorithm is one of the first procedures proposed for learning in neural network models and is mostly credited to Rosenblatt.
1 The perceptron learning algorithm is one of the first procedures proposed for learning in neural network models and is mostly credited to Rosenblatt. The algorithm applies only to single layer models
More informationCOMP-4360 Machine Learning Neural Networks
COMP-4360 Machine Learning Neural Networks Jacky Baltes Autonomous Agents Lab University of Manitoba Winnipeg, Canada R3T 2N2 Email: jacky@cs.umanitoba.ca WWW: http://www.cs.umanitoba.ca/~jacky http://aalab.cs.umanitoba.ca
More informationFEEDBACK GMDH-TYPE NEURAL NETWORK AND ITS APPLICATION TO MEDICAL IMAGE ANALYSIS OF LIVER CANCER. Tadashi Kondo and Junji Ueno
International Journal of Innovative Computing, Information and Control ICIC International c 2012 ISSN 1349-4198 Volume 8, Number 3(B), March 2012 pp. 2285 2300 FEEDBACK GMDH-TYPE NEURAL NETWORK AND ITS
More informationA New Hybrid System for Recognition of Handwritten-Script
computing@tanet.edu.te.ua www.tanet.edu.te.ua/computing ISSN 177-69 A New Hybrid System for Recognition of Handwritten-Script Khalid Saeed 1) and Marek Tabdzki ) Faculty of Computer Science, Bialystok
More informationArtificial Neural Networks
Artificial Neural Networks Threshold units Gradient descent Multilayer networks Backpropagation Hidden layer representations Example: Face Recognition Advanced topics 1 Connectionist Models Consider humans:
More informationMachine Learning. Neural Networks. (slides from Domingos, Pardo, others)
Machine Learning Neural Networks (slides from Domingos, Pardo, others) Human Brain Neurons Input-Output Transformation Input Spikes Output Spike Spike (= a brief pulse) (Excitatory Post-Synaptic Potential)
More informationPattern Recognition Prof. P. S. Sastry Department of Electronics and Communication Engineering Indian Institute of Science, Bangalore
Pattern Recognition Prof. P. S. Sastry Department of Electronics and Communication Engineering Indian Institute of Science, Bangalore Lecture - 27 Multilayer Feedforward Neural networks with Sigmoidal
More informationArtificial Intelligence (AI) Common AI Methods. Training. Signals to Perceptrons. Artificial Neural Networks (ANN) Artificial Intelligence
Artificial Intelligence (AI) Artificial Intelligence AI is an attempt to reproduce intelligent reasoning using machines * * H. M. Cartwright, Applications of Artificial Intelligence in Chemistry, 1993,
More informationCourse 395: Machine Learning - Lectures
Course 395: Machine Learning - Lectures Lecture 1-2: Concept Learning (M. Pantic) Lecture 3-4: Decision Trees & CBC Intro (M. Pantic & S. Petridis) Lecture 5-6: Evaluating Hypotheses (S. Petridis) Lecture
More informationSections 18.6 and 18.7 Analysis of Artificial Neural Networks
Sections 18.6 and 18.7 Analysis of Artificial Neural Networks CS4811 - Artificial Intelligence Nilufer Onder Department of Computer Science Michigan Technological University Outline Univariate regression
More informationVC-dimension of a context-dependent perceptron
1 VC-dimension of a context-dependent perceptron Piotr Ciskowski Institute of Engineering Cybernetics, Wroc law University of Technology, Wybrzeże Wyspiańskiego 27, 50 370 Wroc law, Poland cis@vectra.ita.pwr.wroc.pl
More informationEfficient Forecasting of Exchange rates with Recurrent FLANN
IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661, p- ISSN: 2278-8727Volume 13, Issue 6 (Jul. - Aug. 2013), PP 21-28 Efficient Forecasting of Exchange rates with Recurrent FLANN 1 Ait Kumar
More information