Neural Networks Kohonen Self-Organizing Maps
|
|
|
- Abigayle York
- 9 years ago
- Views:
Transcription
1 Neural Networks Kohonen Self-Organizing Maps Mohamed Krini Christian-Albrechts-Universität zu Kiel Faculty of Engineering Institute of Electrical and Information Engineering Digital Signal Processing and System Theory
2 Contents of the Lecture Entire Semester Introduction Pre-Processing and Feature Extraction Threshold Logic Units - Single Perceptrons Multilayer Perceptrons Training Multilayer Perceptrons Radial Basis Function Networks Learning Vector Quantization Kohonen Self-Organizing Maps Hopfield and Recurrent Networks Slide VIII-2
3 Contents of this Part Kohonen Self-Organizing Maps Introduction Definitions and Properties Neighborhood of Output Neurons Learning Rule Topology Functions Examples Applications Literature Slide VIII-3
4 Introduction Structure of a Self-Organizing Map: Output neurons and their neighborhood relationships The map shows the output neurons and the neighborhood relationships. These neighborhood relationships are called topology. Connections Each input neuron is connected to all output neurons. Input neurons Slide VIII-4
5 Definitions and Properties (1/2) Definitions: A self-organizing map (SOM) or Kohonen feature map is a two layer network without hidden neurons: All input neurons are connected to all output neurons: The distance between the input and the weight vectors is used as input function, similar to RBFN. The activation function is a radial function, i.e. a monotonously decreasing function: The identity is used as output function for each output neuron. Slide VIII-5
6 Definitions and Properties (2/2) Properties: The neurons are interconnected by neighborhood relationships. These relationships are called topology which is described by a distance function: The training of a SOM is highly influenced by its topology. A SOM always activates the neuron with the least distance to an input pattern (principle of winner-takes-all is often used). In absence of neighborhood relationships the SOM operates as vector quantization of the input space. Self-Organizing Maps are networks trained without a teacher. Slide VIII-6
7 Neighborhood of Output Neurons One-Dimensional Topology: Two-Dimensional Topology: Two example topologies of a self-organizing map. Black lines indicate neighbors of a neuron. Gray lines indicate regions assigned to neurons. Topologies with more dimensions would also be possible. They are often not employed due to visualization complexity. Slide VIII-7
8 Learning Rule (1/2) Training Procedure: 1. The network starts with random neuron centers 2. An input vector is selected from the input space. 3. The distance is determined for every neuron. The winner neuron with the maximum activation is selected. 4. The reference vectors are updated using a neighborhood function and the update rule: Neighborhood radius 5. The training is continued with step 2 as long as the maximum number of iterations is not reached. Slide VIII-8
9 Learning Rule (2/2) Training Parameters: The function, also called topology function, represents the neighborhood relationships between the neurons. Note that the function is defined on the grid and not on the input space. The function can be any unimodal function that reaches its maximum at. Time-varying learning rate: Time-varying neighborhood radius: Slide VIII-9
10 Topology Functions (1/2) Common Topology Function: A common topology function is the Gaussian function: with represents the neuron positions on the grid, not on the input space. denotes the winner neuron position. Other functions, such as the cone function or the Mexican hat function, can also be used. Slide VIII-10
11 Topology Functions (2/2) Different Functions: Gaussian Triangular Mexican Hat Rectangle Slide VIII-11
12 Examples Two Dimension Topology (1/3) Unfolding of a Two-Dimensional Self-Organizing Map: 10x10 output neurons were used for the two-dimensional topology. Training patterns randomly distributed within the interval are utilized. Random initialization of the reference vectors. Nearest neighbor neurons are connected by a straight line. Learning rate Neighborhood radius Gaussian topology function is used. Slide VIII-12
13 Examples Two Dimension Topology (2/3) Unfolding of a Two-Dimensional Self-Organizing Map (continued): Initial state Slide VIII-13
14 Examples Two Dimension Topology (3/3) Activation of the Output Neurons: (Input pattern:, Gaussian activation function) Slide VIII-14
15 Examples One Dimension Topology Unfolding of a One-Dimensional Self Organizing Map: Initial state Slide VIII-15
16 Examples Failure of the Training Unfolding of a Two-Dimensional Map Inappropriate Initialization: If the initialization is not chosen appropriately, e.g. if the learning rate or the neighborhood radius parameters are chosen too low, the training of a selforganizing network may fail. Examples on the left demonstrate the maps at iteration 1000, 10000, and The maps are not correctly unfolded. Slide VIII-16
17 Examples Dimension Reduction 2D Self Organizing Map in a 3D Input Space: Self-organizing maps were trained with random points of a rotation parabola (upper graphs) and of a cubic function (lower graphs). Three input neurons are used. Initial state State after iterations A map with 10x10 output neurons is utilized. Reference vectors of adjacent output neurons are connected by a straight line. Original and image space have different dimensions. Self-organizing maps can be used for dimensionality reduction. Slide VIII-17
18 Applications Speech Recognition Phoneme Map in Finnish: a a a ah h ae ae o a a h r ae l o o a r r r g o o r r r m m Part of (hexagonal) feature map Phonemes are extracted from the input signal using the FFT, logarithm, averaging and normalization. During learning, each neuron begins to respond strongly to a specific phoneme. A specific neuron is most active after the training. Some nodes and their phoneme labels are shown on the left. The map works very well in Finnish (phonetic language). Slide VIII-18
19 Applications Dimension Reduction (1/3) dove hen duck goose owl hawk eagle fox wolf dog cat tiger lion horse zebra small medium big legs legs hair hooves mane feathers hunt run fly swim cow Animal Names and Attributes: Each column is a description of an animal, based on the presence (=1) or absence (=0) of some of the 13 different attributes given on the left. Each animal was encoded by a 29- dim data vector: a 13-dimensional vector for the attributes and a 16- dimensional vector for the animal name (vector in which only the element corresponding to the animal has a non-zero value). Slide VIII-19
20 Applications Dimension Reduction (2/3) Trained Network: duck * * horse * * * cow * * * * * * zebra * * * * * * * * * * * * * * tiger goose * * * * * wolf * * * * * * hawk * * * * * * * * owl * * * * * * lion dove * * * * * dog * * * * * * * * * * * * * * * * eagle * * * * * * hen * * * * * fox * * cat A Kohonen Network of 10 x 10 x 29 was utilized. The network was trained for 2000 epochs. The map shows the cells giving the strongest response when only the animal name is presented as input (the dots indicate neurons with weaker responses). Slide VIII-20
21 Applications Dimension Reduction (3/3) Contextual Map: duck duck horse horse zebra zebra cow cow cow cow duck duck horse zebra zebra zebra cow cow tiger tiger goose goose goose zebra zebra zebra wolf wolf tiger tiger goose goose hawk hawk hawk wolf wolf wolf tiger tiger goose owl hawk hawk hawk wolf wolf wolf lion lion dove owl owl hawk hawk dog dog dog lion lion dove dove owl owl owl dog dog dog dog lion dove dove eagle eagle eagle dog dog dog dog cat hen hen Eagle eagle eagle fox fox fox cat cat hen hen eagle eagle eagle fox fox fox cat cat This map shows the result of a simulated electrode penetration mapping". Each cell has been labeled with the animal name that is its best stimulus, i.e., elicits the strongest response for that cell. The result is a contextual map. Similar animals are adjacent. Slide VIII-21
22 Literature Further details can be found in: S. Haykin: Neural Networks and Learning Machines (Chapter 9), Prentice-Hall, 3rd edition, C. Borgelt, F. Klawonn, R. Kruse, D. Nauck: Neuro-Fuzzy-Systeme (Chapter 6), Vieweg Verlag, Wiesbaden, 2003 (in German). R. Rojas: Neural Networks A Systematic Introduction (Chapter 15), Springer, Berlin, Germany, H. Ritter, T. Kohonen: Self-Organizing Semantic Maps, Biol. Cybern. 61, , Springer, D. Kriesel: A Brief Introduction to Neural Networks (chapter 10), Slide VIII-22
Self-Organizing g Maps (SOM) COMP61021 Modelling and Visualization of High Dimensional Data
Self-Organizing g Maps (SOM) Ke Chen Outline Introduction ti Biological Motivation Kohonen SOM Learning Algorithm Visualization Method Examples Relevant Issues Conclusions 2 Introduction Self-organizing
Self Organizing Maps: Fundamentals
Self Organizing Maps: Fundamentals Introduction to Neural Networks : Lecture 16 John A. Bullinaria, 2004 1. What is a Self Organizing Map? 2. Topographic Maps 3. Setting up a Self Organizing Map 4. Kohonen
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
UNIVERSITY OF BOLTON SCHOOL OF ENGINEERING MS SYSTEMS ENGINEERING AND ENGINEERING MANAGEMENT SEMESTER 1 EXAMINATION 2015/2016 INTELLIGENT SYSTEMS
TW72 UNIVERSITY OF BOLTON SCHOOL OF ENGINEERING MS SYSTEMS ENGINEERING AND ENGINEERING MANAGEMENT SEMESTER 1 EXAMINATION 2015/2016 INTELLIGENT SYSTEMS MODULE NO: EEM7010 Date: Monday 11 th January 2016
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
Visualization of Breast Cancer Data by SOM Component Planes
International Journal of Science and Technology Volume 3 No. 2, February, 2014 Visualization of Breast Cancer Data by SOM Component Planes P.Venkatesan. 1, M.Mullai 2 1 Department of Statistics,NIRT(Indian
Classification of Engineering Consultancy Firms Using Self-Organizing Maps: A Scientific Approach
International Journal of Civil & Environmental Engineering IJCEE-IJENS Vol:13 No:03 46 Classification of Engineering Consultancy Firms Using Self-Organizing Maps: A Scientific Approach Mansour N. Jadid
Neural Network Add-in
Neural Network Add-in Version 1.5 Software User s Guide Contents Overview... 2 Getting Started... 2 Working with Datasets... 2 Open a Dataset... 3 Save a Dataset... 3 Data Pre-processing... 3 Lagging...
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
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
Monitoring of Complex Industrial Processes based on Self-Organizing Maps and Watershed Transformations
Monitoring of Complex Industrial Processes based on Self-Organizing Maps and Watershed Transformations Christian W. Frey 2012 Monitoring of Complex Industrial Processes based on Self-Organizing Maps and
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
Load balancing in a heterogeneous computer system by self-organizing Kohonen network
Bull. Nov. Comp. Center, Comp. Science, 25 (2006), 69 74 c 2006 NCC Publisher Load balancing in a heterogeneous computer system by self-organizing Kohonen network Mikhail S. Tarkov, Yakov S. Bezrukov Abstract.
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
Chapter 2 The Research on Fault Diagnosis of Building Electrical System Based on RBF Neural Network
Chapter 2 The Research on Fault Diagnosis of Building Electrical System Based on RBF Neural Network Qian Wu, Yahui Wang, Long Zhang and Li Shen Abstract Building electrical system fault diagnosis is the
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
Advanced Web Usage Mining Algorithm using Neural Network and Principal Component Analysis
Advanced Web Usage Mining Algorithm using Neural Network and Principal Component Analysis Arumugam, P. and Christy, V Department of Statistics, Manonmaniam Sundaranar University, Tirunelveli, Tamilnadu,
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
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 [email protected] Supervisor: Professor Joaquim Marques de Sá June 2006
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
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,
Network Intrusion Detection Using an Improved Competitive Learning Neural Network
Network Intrusion Detection Using an Improved Competitive Learning Neural Network John Zhong Lei and Ali Ghorbani Faculty of Computer Science University of New Brunswick Fredericton, NB, E3B 5A3, Canada
A Computational Framework for Exploratory Data Analysis
A Computational Framework for Exploratory Data Analysis Axel Wismüller Depts. of Radiology and Biomedical Engineering, University of Rochester, New York 601 Elmwood Avenue, Rochester, NY 14642-8648, U.S.A.
1. Classification problems
Neural and Evolutionary Computing. Lab 1: Classification problems Machine Learning test data repository Weka data mining platform Introduction Scilab 1. Classification problems The main aim of a classification
Models of Cortical Maps II
CN510: Principles and Methods of Cognitive and Neural Modeling Models of Cortical Maps II Lecture 19 Instructor: Anatoli Gorchetchnikov dy dt The Network of Grossberg (1976) Ay B y f (
SUCCESSFUL PREDICTION OF HORSE RACING RESULTS USING A NEURAL NETWORK
SUCCESSFUL PREDICTION OF HORSE RACING RESULTS USING A NEURAL NETWORK N M Allinson and D Merritt 1 Introduction This contribution has two main sections. The first discusses some aspects of multilayer perceptrons,
The Research of Data Mining Based on Neural Networks
2011 International Conference on Computer Science and Information Technology (ICCSIT 2011) IPCSIT vol. 51 (2012) (2012) IACSIT Press, Singapore DOI: 10.7763/IPCSIT.2012.V51.09 The Research of Data Mining
Segmentation of stock trading customers according to potential value
Expert Systems with Applications 27 (2004) 27 33 www.elsevier.com/locate/eswa Segmentation of stock trading customers according to potential value H.W. Shin a, *, S.Y. Sohn b a Samsung Economy Research
INTRUSION DETECTION SYSTEM USING SELF ORGANIZING MAP
Acta Electrotechnica et Informatica No. 1, Vol. 6, 2006 1 INTRUSION DETECTION SYSTEM USING SELF ORGANIZING MAP Liberios VOKOROKOS, Anton BALÁŽ, Martin CHOVANEC Technical University of Košice, Faculty of
Content Based Analysis of Email Databases Using Self-Organizing Maps
A. Nürnberger and M. Detyniecki, "Content Based Analysis of Email Databases Using Self-Organizing Maps," Proceedings of the European Symposium on Intelligent Technologies, Hybrid Systems and their implementation
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,
ViSOM A Novel Method for Multivariate Data Projection and Structure Visualization
IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 13, NO. 1, JANUARY 2002 237 ViSOM A Novel Method for Multivariate Data Projection and Structure Visualization Hujun Yin Abstract When used for visualization of
QoS Mapping of VoIP Communication using Self-Organizing Neural Network
QoS Mapping of VoIP Communication using Self-Organizing Neural Network Masao MASUGI NTT Network Service System Laboratories, NTT Corporation -9- Midori-cho, Musashino-shi, Tokyo 80-88, Japan E-mail: [email protected]
Data Mining and Neural Networks in Stata
Data Mining and Neural Networks in Stata 2 nd Italian Stata Users Group Meeting Milano, 10 October 2005 Mario Lucchini e Maurizo Pisati Università di Milano-Bicocca [email protected] [email protected]
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)
9. Text & Documents. Visualizing and Searching Documents. Dr. Thorsten Büring, 20. Dezember 2007, Vorlesung Wintersemester 2007/08
9. Text & Documents Visualizing and Searching Documents Dr. Thorsten Büring, 20. Dezember 2007, Vorlesung Wintersemester 2007/08 Slide 1 / 37 Outline Characteristics of text data Detecting patterns SeeSoft
An Analysis on Density Based Clustering of Multi Dimensional Spatial Data
An Analysis on Density Based Clustering of Multi Dimensional Spatial Data K. Mumtaz 1 Assistant Professor, Department of MCA Vivekanandha Institute of Information and Management Studies, Tiruchengode,
Visualization of Topology Representing Networks
Visualization of Topology Representing Networks Agnes Vathy-Fogarassy 1, Agnes Werner-Stark 1, Balazs Gal 1 and Janos Abonyi 2 1 University of Pannonia, Department of Mathematics and Computing, P.O.Box
MANAGING QUEUE STABILITY USING ART2 IN ACTIVE QUEUE MANAGEMENT FOR CONGESTION CONTROL
MANAGING QUEUE STABILITY USING ART2 IN ACTIVE QUEUE MANAGEMENT FOR CONGESTION CONTROL G. Maria Priscilla 1 and C. P. Sumathi 2 1 S.N.R. Sons College (Autonomous), Coimbatore, India 2 SDNB Vaishnav College
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,
USING SELF-ORGANIZING MAPS FOR INFORMATION VISUALIZATION AND KNOWLEDGE DISCOVERY IN COMPLEX GEOSPATIAL DATASETS
USING SELF-ORGANIZING MAPS FOR INFORMATION VISUALIZATION AND KNOWLEDGE DISCOVERY IN COMPLEX GEOSPATIAL DATASETS Koua, E.L. International Institute for Geo-Information Science and Earth Observation (ITC).
Methodology for Emulating Self Organizing Maps for Visualization of Large Datasets
Methodology for Emulating Self Organizing Maps for Visualization of Large Datasets Macario O. Cordel II and Arnulfo P. Azcarraga College of Computer Studies *Corresponding Author: [email protected]
Supporting Online Material for
www.sciencemag.org/cgi/content/full/313/5786/504/dc1 Supporting Online Material for Reducing the Dimensionality of Data with Neural Networks G. E. Hinton* and R. R. Salakhutdinov *To whom correspondence
Cognitive Dynamics - Dynamic Cognition?
Cognitive Dynamics - Dynamic Cognition? Reginald Ferber 1 Fachbereich 2 Universität GH Paderborn D-33095 Paderborn, Germany 2 Abstract: In the last ten years a paradigm shift took place in cognitive science.
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/
Artificial Neural Network for Speech Recognition
Artificial Neural Network for Speech Recognition Austin Marshall March 3, 2005 2nd Annual Student Research Showcase Overview Presenting an Artificial Neural Network to recognize and classify speech Spoken
SEARCH AND CLASSIFICATION OF "INTERESTING" BUSINESS APPLICATIONS IN THE WORLD WIDE WEB USING A NEURAL NETWORK APPROACH
SEARCH AND CLASSIFICATION OF "INTERESTING" BUSINESS APPLICATIONS IN THE WORLD WIDE WEB USING A NEURAL NETWORK APPROACH Abstract Karl Kurbel, Kirti Singh, Frank Teuteberg Europe University Viadrina Frankfurt
CS 2750 Machine Learning. Lecture 1. Machine Learning. http://www.cs.pitt.edu/~milos/courses/cs2750/ CS 2750 Machine Learning.
Lecture Machine Learning Milos Hauskrecht [email protected] 539 Sennott Square, x5 http://www.cs.pitt.edu/~milos/courses/cs75/ Administration Instructor: Milos Hauskrecht [email protected] 539 Sennott
A Partially Supervised Metric Multidimensional Scaling Algorithm for Textual Data Visualization
A Partially Supervised Metric Multidimensional Scaling Algorithm for Textual Data Visualization Ángela Blanco Universidad Pontificia de Salamanca [email protected] Spain Manuel Martín-Merino Universidad
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
Data Mining Techniques Chapter 7: Artificial Neural Networks
Data Mining Techniques Chapter 7: Artificial Neural Networks Artificial Neural Networks.................................................. 2 Neural network example...................................................
LVQ Plug-In Algorithm for SQL Server
LVQ Plug-In Algorithm for SQL Server Licínia Pedro Monteiro Instituto Superior Técnico [email protected] I. Executive Summary In this Resume we describe a new functionality implemented
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
A New Approach For Estimating Software Effort Using RBFN Network
IJCSNS International Journal of Computer Science and Network Security, VOL.8 No.7, July 008 37 A New Approach For Estimating Software Using RBFN Network Ch. Satyananda Reddy, P. Sankara Rao, KVSVN Raju,
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
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
Introduction to Machine Learning and Data Mining. Prof. Dr. Igor Trajkovski [email protected]
Introduction to Machine Learning and Data Mining Prof. Dr. Igor Trakovski [email protected] Neural Networks 2 Neural Networks Analogy to biological neural systems, the most robust learning systems
ultra fast SOM using CUDA
ultra fast SOM using CUDA SOM (Self-Organizing Map) is one of the most popular artificial neural network algorithms in the unsupervised learning category. Sijo Mathew Preetha Joy Sibi Rajendra Manoj A
Online data visualization using the neural gas network
Online data visualization using the neural gas network Pablo A. Estévez, Cristián J. Figueroa Department of Electrical Engineering, University of Chile, Casilla 412-3, Santiago, Chile Abstract A high-quality
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
Hybrid Evolution of Heterogeneous Neural Networks
Hybrid Evolution of Heterogeneous Neural Networks 01001110 01100101 01110101 01110010 01101111 01101110 01101111 01110110 01100001 00100000 01110011 01101011 01110101 01110000 01101001 01101110 01100001
Visualization of textual data: unfolding the Kohonen maps.
Visualization of textual data: unfolding the Kohonen maps. CNRS - GET - ENST 46 rue Barrault, 75013, Paris, France (e-mail: [email protected]) Ludovic Lebart Abstract. The Kohonen self organizing
Data topology visualization for the Self-Organizing Map
Data topology visualization for the Self-Organizing Map Kadim Taşdemir and Erzsébet Merényi Rice University - Electrical & Computer Engineering 6100 Main Street, Houston, TX, 77005 - USA Abstract. The
On the use of Three-dimensional Self-Organizing Maps for Visualizing Clusters in Geo-referenced Data
On the use of Three-dimensional Self-Organizing Maps for Visualizing Clusters in Geo-referenced Data Jorge M. L. Gorricha and Victor J. A. S. Lobo CINAV-Naval Research Center, Portuguese Naval Academy,
Quality Assessment in Spatial Clustering of Data Mining
Quality Assessment in Spatial Clustering of Data Mining Azimi, A. and M.R. Delavar Centre of Excellence in Geomatics Engineering and Disaster Management, Dept. of Surveying and Geomatics Engineering, Engineering
Local Anomaly Detection for Network System Log Monitoring
Local Anomaly Detection for Network System Log Monitoring Pekka Kumpulainen Kimmo Hätönen Tampere University of Technology Nokia Siemens Networks [email protected] [email protected] Abstract
Neural Networks for Intrusion Detection and Its Applications
, July 3-5, 2013, London, U.K. Neural Networks for Intrusion Detection and Its Applications E.Kesavulu Reddy, Member IAENG Abstract: With rapid expansion of computer networks during the past decade, security
AUTOMATION OF ENERGY DEMAND FORECASTING. Sanzad Siddique, B.S.
AUTOMATION OF ENERGY DEMAND FORECASTING by Sanzad Siddique, B.S. A Thesis submitted to the Faculty of the Graduate School, Marquette University, in Partial Fulfillment of the Requirements for the Degree
Self Organizing Maps for Visualization of Categories
Self Organizing Maps for Visualization of Categories Julian Szymański 1 and Włodzisław Duch 2,3 1 Department of Computer Systems Architecture, Gdańsk University of Technology, Poland, [email protected]
TRAIN AND ANALYZE NEURAL NETWORKS TO FIT YOUR DATA
TRAIN AND ANALYZE NEURAL NETWORKS TO FIT YOUR DATA TRAIN AND ANALYZE NEURAL NETWORKS TO FIT YOUR DATA September 2005 First edition Intended for use with Mathematica 5 Software and manual written by: Jonas
Visualizing an Auto-Generated Topic Map
Visualizing an Auto-Generated Topic Map Nadine Amende 1, Stefan Groschupf 2 1 University Halle-Wittenberg, information manegement technology [email protected] 2 media style labs Halle Germany [email protected]
Grid e-services for Multi-Layer SOM Neural Network Simulation
Grid e-services for Multi-Layer SOM Neural Network Simulation,, Rui Silva Faculdade de Engenharia 4760-108 V. N. Famalicão, Portugal {rml,rsilva}@fam.ulusiada.pt 2007 Outline Overview Multi-Layer SOM Background
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
Cluster Analysis: Advanced Concepts
Cluster Analysis: Advanced Concepts and dalgorithms Dr. Hui Xiong Rutgers University Introduction to Data Mining 08/06/2006 1 Introduction to Data Mining 08/06/2006 1 Outline Prototype-based Fuzzy c-means
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
Weathervanes. The finishing touch
Weathervanes The finishing touch Large Rooster Height 625mm, length 475mm Extra Large Rooster Height 800mm, length 725mm. Standard Rooster Height 500mm, length 400mm. Crowing Rooster Height 470mm, length
CITY UNIVERSITY OF HONG KONG 香 港 城 市 大 學. Self-Organizing Map: Visualization and Data Handling 自 組 織 神 經 網 絡 : 可 視 化 和 數 據 處 理
CITY UNIVERSITY OF HONG KONG 香 港 城 市 大 學 Self-Organizing Map: Visualization and Data Handling 自 組 織 神 經 網 絡 : 可 視 化 和 數 據 處 理 Submitted to Department of Electronic Engineering 電 子 工 程 學 系 in Partial Fulfillment
COMPARISON OF OBJECT BASED AND PIXEL BASED CLASSIFICATION OF HIGH RESOLUTION SATELLITE IMAGES USING ARTIFICIAL NEURAL NETWORKS
COMPARISON OF OBJECT BASED AND PIXEL BASED CLASSIFICATION OF HIGH RESOLUTION SATELLITE IMAGES USING ARTIFICIAL NEURAL NETWORKS B.K. Mohan and S. N. Ladha Centre for Studies in Resources Engineering IIT
Comparing large datasets structures through unsupervised learning
Comparing large datasets structures through unsupervised learning Guénaël Cabanes and Younès Bennani LIPN-CNRS, UMR 7030, Université de Paris 13 99, Avenue J-B. Clément, 93430 Villetaneuse, France [email protected]
Data Mining. Cluster Analysis: Advanced Concepts and Algorithms
Data Mining Cluster Analysis: Advanced Concepts and Algorithms Tan,Steinbach, Kumar Introduction to Data Mining 4/18/2004 1 More Clustering Methods Prototype-based clustering Density-based clustering Graph-based
A Discussion on Visual Interactive Data Exploration using Self-Organizing Maps
A Discussion on Visual Interactive Data Exploration using Self-Organizing Maps Julia Moehrmann 1, Andre Burkovski 1, Evgeny Baranovskiy 2, Geoffrey-Alexeij Heinze 2, Andrej Rapoport 2, and Gunther Heidemann
Mobile Phone APP Software Browsing Behavior using Clustering Analysis
Proceedings of the 2014 International Conference on Industrial Engineering and Operations Management Bali, Indonesia, January 7 9, 2014 Mobile Phone APP Software Browsing Behavior using Clustering Analysis
Credit Card Fraud Detection Using Self Organised Map
International Journal of Information & Computation Technology. ISSN 0974-2239 Volume 4, Number 13 (2014), pp. 1343-1348 International Research Publications House http://www. irphouse.com Credit Card Fraud
PRACTICAL DATA MINING IN A LARGE UTILITY COMPANY
QÜESTIIÓ, vol. 25, 3, p. 509-520, 2001 PRACTICAL DATA MINING IN A LARGE UTILITY COMPANY GEORGES HÉBRAIL We present in this paper the main applications of data mining techniques at Electricité de France,
KATE GLEASON COLLEGE OF ENGINEERING. John D. Hromi Center for Quality and Applied Statistics
ROCHESTER INSTITUTE OF TECHNOLOGY COURSE OUTLINE FORM KATE GLEASON COLLEGE OF ENGINEERING John D. Hromi Center for Quality and Applied Statistics NEW (or REVISED) COURSE (KGCOE- CQAS- 747- Principles of
DOG Pets cat - dog - horse - hamster - rabbit - fish
CAT Pets cat - dog - horse - hamster - rabbit - fish DOG Pets cat - dog - horse - hamster - rabbit - fish HORSE Pets cat - dog - horse - hamster - rabbit - fish HAMSTER Pets cat - dog - horse - hamster
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,
