Distributed Problem Solving Based on Recurrent Neural Networks Applied to Computer Network Management
|
|
- Arnold Francis
- 6 years ago
- Views:
Transcription
1 Distributed Problem Solving Based on Recurrent Neural Networks Applied to Computer Network Management Analúcia Schiaffino Morales De Franceschi Jorge M. Barreto* Department of Electrical Engineering, Biomedical Engineering Research Group *Informatics and Statistics Department UNIVERSIDADE FEDERAL DE SANTA CATARINA PO. Box 476 Trindade Phone: Fax: Florianópolis- Santa Catarina - Brazil Abstract With the application of new techniques, such as autonomous agents, artificial neural networks (ANN) and evolutionary computation, new questions arrive and may be, the most important areis: "can new problems be solved?" and "with how much effort?" This is particularly important when neural networks are used, since where a new computer paradigm is involved and a connectionist computability and complexity theory are still missing. To attach this problem we are developing some software autonomous agents based on recurrent neural networks. Observing the emergent behavior of ANN autonomous agents, and considering the initial results on complexity connectionist theory, a neural network for computer network management is developed.and presented 1 Introduction Application of new techniques to complex problem solving such as autonomous agents, artificial neural networks (ANN) and evolutionary computation have been growing up. With these new tools arrives new questionsnew question arrives and, the most important is: "can new problems be solved? with how much effort?" This is particularly important with neural networks where a new computer paradigm is involved and the construction of a connectionist computability and complexity theory must be accomplished. Neural computability was treated initially by McCulloch & Pitts using logic [1]. They proved the equivalence of a neural network with input devices and a Turing Machine. After, Arbib proposed an
2 intuitive demonstration of this equivalence [2]. However, in the complexity field, the two approaches are different because they require different resources. Minsky and Papert [3] provided the first contribution to such theory when they proved that a feed forward ANN must have a hidden layer o solve a non-linearly separable problem. Another result is that to solve a dynamical problem a recurrent dynamical ANN is simpler than a feed forward ANN one [4]. In the scientific literature, it is usual to find dynamic problems solved by static feed forward neural networks. In some formusing this approach, explicitly or implicitly the state of the dynamical system must be supplied, leading to a very big neural network and a corresponding longer training time even if the famous back propagation is used. To obtain a dynamical neural network it is possible: To apply a sequential line of time delays between each two inputs of a feed forward neural network; Using a network with cycles and dynamical neurons (ex: Hopfield network and recuurent neural networks). This work outlines the employment use of recurrent neural networks as distributed problem solving of the computer network management. It is organized in fivesix sections, the first beeing this one. The second presents the problem and approach which is based on application of the dynamic system to solve a distributed problem. The third section illustrates a simple example about recurrent neural network usage, and demonstrates why we should use dynamic systems. A distributed problem is outlined in four section four. And finally, following the conclusion and the respective references. 2 Recurrent Neural Networks Recurrent neural networks had been characterized by cycles, they have one or more in theiryour topology. They aremay be built with dynamical neurons and or have a sequential line of delays in the recursive conexion between the neuronsin one of layers. These delay elements are denoted in the text by z -1. The dynamical character feature of these topology permits the state representation and may be used in voice processing, industrial control and adaptive signal processing. Analysis of this topology allows to conclude that: It is applicable to computer network management because the network systems must be treated as dynamics systems. If a static neural network was used in a network system, then this neural network can not be used if the topology of this network was changed. The network management claims skill personnel, able to detect, diagnose and correct problems quickly and accurately, preferably before they affect the user community [5]. A recurrent neural network is able to implement this functions accurately and quickly after the training. Acho que podia botar uma figura de uma rede neural recorrente 3 Example 1 Parity Agent To attach? this problem we are developing some software autonomous agents based on recurrent neural networks [6]. The prototype was designed using JAVA and C language. Following two examples of these
3 agents. The first is a simple parity agent which serves as a didactic example and the second an interpreter network event agent which is a distributed version of an autonomous agent. To illustrate the fact that a recursive network can solve a dynamical problem with less neurons than a feed forward network let us Suppose suppose the 7-bit parity problem. It can be solved although a static feed forward network (Figure 1-B). However this solution is valid only for 7 bits. Another and more efficient approach is to use a recurrent neural network able to learn the parity concept (Figure 1-A) [7]. The recurrent neural network was trained using the synaptic weights from the feed forward 7-bit parity network,. And the start state was considered zero. Once trained, this neural network can solve the parity for any bit long string. Z -1 A A recurrent neural network to solve the n-bit parity problem. B - A classical feed forward neural network to solve a 7-bit parity problem. Figure 1 - Both neural architectures to implement a parity problem. 4 Example 2 - Distributed Solving Problem Dynamic, noisy and non stationary character of computer networks makes it hard to define what a fault is in a network environment. Diagnosis is the identification of a condition by its signs, symptoms or distinguishing characteristics [5]. Consider that the hosts of our test environment are sufficiently sophisticated to report network events. To do so, an autonomous agent has been developed to classify the network event as a Critical, Simple Failure, or No Failure. The agent is an interpreter of network events and would inform you when a problem is detected, by logging network events or by polling. Finding a fault, the agent must act or at least generate an alert to the user. INTERPRETER NETWORK EVENT Polling entry (PE) Event entry (EE) z -1 No Failure (NF) Simple Failure (SF) Critical Failure (CF)
4 Figure 2 - Recurrent neural network to implement the interpreter agent. The network was trained with the pattern shown in (Table 1) and the network implemented as illustrated in Figure 2. If was setting the polling and event entry then the system will classify as a critical failure then alert user. A simple failure will be characterized when one of the entries was setting. And classify as no failure when the system was reset. Table 1 - The pattern used to train the neural network. PE EE NF SF CF To distributed problem solutions we are using the networking features of JAVA language, and this example will receive the signals from a ping command. This command needs to know about dropped to determine how good or bad the connection is. This may be interpreted by using the recurrent network above. Talvez desse pra desenvolver mais esta parte de solução distribuida (eu não entendi muito bem). 5 Conclusion The use of artificial intelligence is justified through the growing of the networks and the necessity of reliable services. A quick cost-benefit survey shows the following advantages [8]: Better quality of service: with the dissemination of the specialist throughout all segments of the network. The administrator's task is facilitated, providing a better performance; Greater agility, lower costs and greater productivity in the execution of services permitted by automation; Higher reliability, with decreased decision-making time; Training support for improved human resources preparation. In this sense, this work analyses the following questions: What kind of ANN must be used to solve the fault or performance management problem?; or, How rich must the hidden layer be to solve a distributed problem?; and, How may we construct a proactive network management using recurrent neural networks?. Koch [9], utilized autonomous agents based on ANN (classical feed forward with trained by back propagation) applied to management of computer networks. And iin 1997 a prototype employing artificial intelligence techniques to proactive network management was developed using the symbolic paradigm which were designed by observing the Ethernet network behavior [10][11][12][13]. In fact, these work
5 applied a dynamic character to a management network system using a recurrent neural networks. The future works are concentrated in develop another applications as mobile and telecommunications agents based in this theory. 6 References [1] McCulloch, W. S. and W. H. Pitts. A Logical Calculus of Ideas Immanent in Nervous Activity, Bull. of Mathematical Biophysics, vol.5, pp , [2] Arbib, M. A. Brains, Machines and Mathematics, McGraw-Hill,1964. [3] M. L. Minsky, S. A. Papert, "Perceptrons: an introduction to computational geometry", MIT Press, 1988 [4] M. Roisenberg, J.M.Barreto, F.M. de Azevedo. "A Neural Network that Implements Reactive Behavior Autonomous Agents". In: IASTED International Conference Artificial Intelligence, Expert Systems and Neural Networks. Honolulu, Hawaii, August 19-21, Pp [5] Maxion, R.A., Feather, F.E. A Case Study of Ethernet Anomalies in a Distributed Computing Environment, IEEE Transactions on Reliability, Vol 39, no. 4, oct., [6] M. Roisenberg, J.M.Barreto, F.M. de Azevedo, L.M.Brasil. "On a Formal Concept of Autonomous Agents". In: 16 th IASTED International Conference Applied Informatics, Germany, February, [7] J.M.Barreto, M.Roisenberg, F.M. de Azevedo. "Developing Artificial Neural Networks for Autonomous Agents Using Evolutionary Programming". In: IASTED International Conference Artificial Intelligence and Soft Computing. Cancun, May, 27-30, Pp [8] A.S.M. De Franceschi, M.A. da Rocha, H.L. Weber, C.B. Westphall, "Employing Remote Monitoring and Artificial Intelligence Techniques to Develop the Proactive Network Management", In IEEE International Workshop on Application of Neural Networks in Telecommunications, Melbourne, pp [9] F. Koch Autonomous Agents for Computer Network Management, M. Sc. Dissertation, Federal University of Santa Catarina, Florianópolis, [10] A.S.M. De Franceschi, M.A. da Rocha, H.L. Weber, C.B. Westphall, "Proactive Network Management Using Remote Monitoring and Artificial Intelligence Techniques", In IEEE International Symposium on Computer Communications, Alexandria, [11] A.S.M. De Franceschi, L.F. Kormann, C.B. Westphall, "Performance Evaluation for Proactive Network Management", in IEEE/ICC 96 International on Communications Conference, Vol. I, Dallas, Texas, Jun., [12] A.S.M. De Franceschi, L.F. Kormann, C.B. Westphall, "A Performance Application for Proactive Network Management", in Second IEEE International Workshop on Management Systems, Toronto, Jun., Pp [13] A.S.M. De Franceschi. "A Performance Application for Proactive Network Management", M. Sc. Dissertation, Federal University of Santa Catarina, Florianópolis, 1996.
Artificial Neural Networks
The Perceptron Rodrigo Fernandes de Mello Invited Professor at Télécom ParisTech Associate Professor at Universidade de São Paulo, ICMC, Brazil http://www.icmc.usp.br/~mello mello@icmc.usp.br Conceptually
More informationALGORITHM AND SOFTWARE BASED ON MLPNN FOR ESTIMATING CHANNEL USE IN THE SPECTRAL DECISION STAGE IN COGNITIVE RADIO NETWORKS
ALGORITHM AND SOFTWARE BASED ON MLPNN FOR ESTIMATING CHANNEL USE IN THE SPECTRAL DECISION STAGE IN COGNITIVE RADIO NETWORKS Johana Hernández Viveros 1, Danilo López Sarmiento 2 and Nelson Enrique Vera
More informationLecture 17: Neural Networks and Deep Learning. Instructor: Saravanan Thirumuruganathan
Lecture 17: Neural Networks and Deep Learning Instructor: Saravanan Thirumuruganathan Outline Perceptron Neural Networks Deep Learning Convolutional Neural Networks Recurrent Neural Networks Auto Encoders
More informationNeural Networks CMSC475/675
Introduction to Neural Networks CMSC475/675 Chapter 1 Introduction Why ANN Introduction Some tasks can be done easily (effortlessly) by humans but are hard by conventional paradigms on Von Neumann machine
More informationGrids of Agents for Computer and Telecommunication Network Management
Grids of Agents for Computer and Telecommunication Network Marcos Dias de Assunção, Carlos Becker Westphall Network and Laboratory Federal University of Santa Catarina Florianópolis, SC, 88049-970, PO
More informationModel-Solver Integration in Decision Support Systems: A Web Services Approach
Model-Solver Integration in Decision Support Systems: A Web Services Approach Keun-Woo Lee a, *, Soon-Young Huh a a Graduate School of Management, Korea Advanced Institute of Science and Technology 207-43
More information6. NEURAL NETWORK BASED PATH PLANNING ALGORITHM 6.1 INTRODUCTION
6 NEURAL NETWORK BASED PATH PLANNING ALGORITHM 61 INTRODUCTION In previous chapters path planning algorithms such as trigonometry based path planning algorithm and direction based path planning algorithm
More informationCOMPUTATIONAL INTELLIGENCE
COMPUTATIONAL INTELLIGENCE Fundamentals Adrian Horzyk Preface Before we can proceed to discuss specific complex methods we have to introduce basic concepts, principles, and models of computational intelligence
More informationA General Method for the Analysis and the Logical Generation of Discrete Mathematical Systems in Programmable Logical Controller
A General Method for the Analysis and the Logical Generation of Discrete Mathematical Systems in Programmable Logical Controller Daniel M. Dubois * Department of Applied Informatics and Artificial Intelligence,
More informationLearning. Learning agents Inductive learning. Neural Networks. Different Learning Scenarios Evaluation
Learning Learning agents Inductive learning Different Learning Scenarios Evaluation Slides based on Slides by Russell/Norvig, Ronald Williams, and Torsten Reil Material from Russell & Norvig, chapters
More informationReview on Methods of Selecting Number of Hidden Nodes in Artificial Neural Network
Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 3, Issue. 11, November 2014,
More informationAssisted Research and Optimization of the proper Neural Network Solving the Inverse Kinematics Problem
ISBN 978--84626-xxx-x Proceedings of 20 International Conference on Optimization of the Robots and Manipulators (OPTIROB 20) Sinaia, Romania, 26-28 Mai, 20, pp. xxx-xxx Assisted Research and Optimization
More informationEdge Detection for Dental X-ray Image Segmentation using Neural Network approach
Volume 1, No. 7, September 2012 ISSN 2278-1080 The International Journal of Computer Science & Applications (TIJCSA) RESEARCH PAPER Available Online at http://www.journalofcomputerscience.com/ Edge Detection
More informationSupervised Learning with Neural Networks. We now look at how an agent might learn to solve a general problem by seeing examples.
Supervised Learning with Neural Networks We now look at how an agent might learn to solve a general problem by seeing examples. Aims: to present an outline of supervised learning as part of AI; to introduce
More informationFault Diagnosis in Turning Operation with Neural Network Approach
Fault Diagnosis in Turning Operation with Neural Network Approach FDD Course Project By: Ensieh Sadat Hosseini Rooteh Supervisor: Professor Youmin Zhang Department of Mechanical and Industrial Engineering
More informationMachine Learning in Biology
Università degli studi di Padova Machine Learning in Biology Luca Silvestrin (Dottorando, XXIII ciclo) Supervised learning Contents Class-conditional probability density Linear and quadratic discriminant
More informationCharacter Recognition Using Convolutional Neural Networks
Character Recognition Using Convolutional Neural Networks David Bouchain Seminar Statistical Learning Theory University of Ulm, Germany Institute for Neural Information Processing Winter 2006/2007 Abstract
More informationSimulation of Back Propagation Neural Network for Iris Flower Classification
American Journal of Engineering Research (AJER) e-issn: 2320-0847 p-issn : 2320-0936 Volume-6, Issue-1, pp-200-205 www.ajer.org Research Paper Open Access Simulation of Back Propagation Neural Network
More informationMONITORING PARAMETER BASED DETERMINATION OF PRODUCTION TOLERANCES
MONITORING PARAMETER BASED DETERMINATION OF PRODUCTION TOLERANCES Zs. J. Viharos 1, L. Monostori 2, K. Novák 3, G. A. Tóth 3 1 Senior research associate, 2 Professor, 3 University Student, Computer and
More informationAn Edge Detection Method Using Back Propagation Neural Network
RESEARCH ARTICLE OPEN ACCESS An Edge Detection Method Using Bac Propagation Neural Netor Ms. Utarsha Kale*, Dr. S. M. Deoar** *Department of Electronics and Telecommunication, Sinhgad Institute of Technology
More informationFor Monday. Read chapter 18, sections Homework:
For Monday Read chapter 18, sections 10-12 The material in section 8 and 9 is interesting, but we won t take time to cover it this semester Homework: Chapter 18, exercise 25 a-b Program 4 Model Neuron
More informationA novel firing rule for training Kohonen selforganising
A novel firing rule for training Kohonen selforganising maps D. T. Pham & A. B. Chan Manufacturing Engineering Centre, School of Engineering, University of Wales Cardiff, P.O. Box 688, Queen's Buildings,
More informationII. ARTIFICIAL NEURAL NETWORK
Applications of Artificial Neural Networks in Power Systems: A Review Harsh Sareen 1, Palak Grover 2 1, 2 HMR Institute of Technology and Management Hamidpur New Delhi, India Abstract: A standout amongst
More informationEUROPEAN ICT PROFESSIONAL ROLE PROFILES VERSION 2 CWA 16458:2018 LOGFILE
EUROPEAN ICT PROFESSIONAL ROLE PROFILES VERSION 2 CWA 16458:2018 LOGFILE Overview all ICT Profile changes in title, summary, mission and from version 1 to version 2 Versions Version 1 Version 2 Role Profile
More informationSupervised Learning (contd) Linear Separation. Mausam (based on slides by UW-AI faculty)
Supervised Learning (contd) Linear Separation Mausam (based on slides by UW-AI faculty) Images as Vectors Binary handwritten characters Treat an image as a highdimensional vector (e.g., by reading pixel
More informationSupervised Learning in Neural Networks (Part 2)
Supervised Learning in Neural Networks (Part 2) Multilayer neural networks (back-propagation training algorithm) The input signals are propagated in a forward direction on a layer-bylayer basis. Learning
More informationMachine Learning in WAN Research
Machine Learning in WAN Research Mariam Kiran mkiran@es.net Energy Sciences Network (ESnet) Lawrence Berkeley National Lab Oct 2017 Presented at Internet2 TechEx 2017 Outline ML in general ML in network
More informationNeural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani
Neural Networks CE-725: Statistical Pattern Recognition Sharif University of Technology Spring 2013 Soleymani Outline Biological and artificial neural networks Feed-forward neural networks Single layer
More informationWebsite: HOPEFIELD NETWORK. Inderjeet Singh Behl, Ankush Saini, Jaideep Verma. ID-
International Journal Of Scientific Research And Education Volume 1 Issue 7 Pages 154-162 2013 ISSN (e): 2321-7545 Website: http://ijsae.in HOPEFIELD NETWORK Inderjeet Singh Behl, Ankush Saini, Jaideep
More informationData Mining. Neural Networks
Data Mining Neural Networks Goals for this Unit Basic understanding of Neural Networks and how they work Ability to use Neural Networks to solve real problems Understand when neural networks may be most
More informationArtificial Neural Network based Curve Prediction
Artificial Neural Network based Curve Prediction LECTURE COURSE: AUSGEWÄHLTE OPTIMIERUNGSVERFAHREN FÜR INGENIEURE SUPERVISOR: PROF. CHRISTIAN HAFNER STUDENTS: ANTHONY HSIAO, MICHAEL BOESCH Abstract We
More informationAnomaly Detection System for Video Data Using Machine Learning
Anomaly Detection System for Video Data Using Machine Learning Tadashi Ogino Abstract We are developing an anomaly detection system for video data that uses machine learning. The proposed system has two
More informationClimate Precipitation Prediction by Neural Network
Journal of Mathematics and System Science 5 (205) 207-23 doi: 0.7265/259-529/205.05.005 D DAVID PUBLISHING Juliana Aparecida Anochi, Haroldo Fraga de Campos Velho 2. Applied Computing Graduate Program,
More informationNeuromorphic Computing: Our approach to developing applications using a new model of computing
Neuromorphic Computing: Our approach to developing applications using a new model of computing David J. Mountain Senior Technical Director Advanced Computing Systems Research Program Background Info Outline
More informationA MAS Based ETL Approach for Complex Data
A MAS Based ETL Approach for Complex Data O. Boussaid, F. Bentayeb, J. Darmont Abstract : In a data warehousing process, the phase of data integration is crucial. Many methods for data integration have
More informationNeuro-fuzzy, GA-Fuzzy, Neural-Fuzzy-GA: A Data Mining Technique for Optimization
International Journal of Computer Science and Software Engineering Volume 3, Number 1 (2017), pp. 1-9 International Research Publication House http://www.irphouse.com Neuro-fuzzy, GA-Fuzzy, Neural-Fuzzy-GA:
More informationArtificial Neural Networks. Introduction to Computational Neuroscience Ardi Tampuu
Artificial Neural Networks Introduction to Computational Neuroscience Ardi Tampuu 7.0.206 Artificial neural network NB! Inspired by biology, not based on biology! Applications Automatic speech recognition
More informationPattern Classification Algorithms for Face Recognition
Chapter 7 Pattern Classification Algorithms for Face Recognition 7.1 Introduction The best pattern recognizers in most instances are human beings. Yet we do not completely understand how the brain recognize
More informationIntroduction to Neural Networks
Introduction to Neural Networks What are connectionist neural networks? Connectionism refers to a computer modeling approach to computation that is loosely based upon the architecture of the brain Many
More informationA framework for network modeling in Prolog
A framework for network modeling in Prolog Zdravko I. Markov Institute of Engineering Cybernetics and Robotics Bulgarian Academy of Sciences Acad.G.Bonchev str. bl.29a f 1113 Sofia, Bulgaria Abstract A
More informationA *69>H>N6 #DJGC6A DG C<>C::G>C<,8>:C8:H /DA 'D 2:6G, ()-"&"3 -"(' ( +-" " " % '.+ % ' -0(+$,
The structure is a very important aspect in neural network design, it is not only impossible to determine an optimal structure for a given problem, it is even impossible to prove that a given structure
More informationLogical Rhythm - Class 3. August 27, 2018
Logical Rhythm - Class 3 August 27, 2018 In this Class Neural Networks (Intro To Deep Learning) Decision Trees Ensemble Methods(Random Forest) Hyperparameter Optimisation and Bias Variance Tradeoff Biological
More informationLecture 5: The Halting Problem. Michael Beeson
Lecture 5: The Halting Problem Michael Beeson Historical situation in 1930 The diagonal method appears to offer a way to extend just about any definition of computable. It appeared in the 1920s that it
More informationClassification of Mammographic Images Using Artificial Neural Networks
Applied Mathematical Sciences, Vol. 7, 2013, no. 89, 4415-4423 HIKARI Ltd, www.m-hikari.com http://dx.doi.org/10.12988/ams.2013.35293 Classification of Mammographic Images Using Artificial Neural Networks
More informationChapter 5 Components for Evolution of Modular Artificial Neural Networks
Chapter 5 Components for Evolution of Modular Artificial Neural Networks 5.1 Introduction In this chapter, the methods and components used for modular evolution of Artificial Neural Networks (ANNs) are
More informationNeural Networks Library in Java TM : a proposal for network intelligent agents
Neural Networks Library in Java TM : a proposal for network intelligent agents Daniele Denaro C.N.R. Institute of Cognitive Sciences and Technology Viale Marx, 5-0037 - Rome (IT) Telephone: +39 06-86090227
More informationParallel Evaluation of Hopfield Neural Networks
Parallel Evaluation of Hopfield Neural Networks Antoine Eiche, Daniel Chillet, Sebastien Pillement and Olivier Sentieys University of Rennes I / IRISA / INRIA 6 rue de Kerampont, BP 818 2232 LANNION,FRANCE
More informationNeural 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 of neural nets are typically dated back to the early 1940 s and work by two physiologists, McCulloch
More informationMachine Learning in WAN Research
Machine Learning in WAN Research Mariam Kiran mkiran@es.net Energy Sciences Network (ESnet) Lawrence Berkeley National Lab Oct 2017 Presented at Internet2 TechEx 2017 Outline ML in general ML in network
More informationAutomatic Machinery Fault Detection and Diagnosis Using Fuzzy Logic
Automatic Machinery Fault Detection and Diagnosis Using Fuzzy Logic Chris K. Mechefske Department of Mechanical and Materials Engineering The University of Western Ontario London, Ontario, Canada N6A5B9
More informationHybrid Feature Selection for Modeling Intrusion Detection Systems
Hybrid Feature Selection for Modeling Intrusion Detection Systems Srilatha Chebrolu, Ajith Abraham and Johnson P Thomas Department of Computer Science, Oklahoma State University, USA ajith.abraham@ieee.org,
More informationAN AGENT BASED INTELLIGENT TUTORING SYSTEM FOR PARAMETER PASSING IN JAVA PROGRAMMING
AN AGENT BASED INTELLIGENT TUTORING SYSTEM FOR PARAMETER PASSING IN JAVA PROGRAMMING 1 Samy Abu Naser 1 Associate Prof., Faculty of Engineering &Information Technology, Al-Azhar University, Gaza, Palestine
More informationReservoir Computing with Emphasis on Liquid State Machines
Reservoir Computing with Emphasis on Liquid State Machines Alex Klibisz University of Tennessee aklibisz@gmail.com November 28, 2016 Context and Motivation Traditional ANNs are useful for non-linear problems,
More informationMultilayer Feed-forward networks
Multi Feed-forward networks 1. Computational models of McCulloch and Pitts proposed a binary threshold unit as a computational model for artificial neuron. This first type of neuron has been generalized
More informationProcedia Computer Science
Procedia Computer Science 3 (2011) 584 588 Procedia Computer Science 00 (2010) 000 000 Procedia Computer Science www.elsevier.com/locate/procedia www.elsevier.com/locate/procedia WCIT 2010 Diagnosing internal
More informationCourse Outcome of M.E (ECE)
Course Outcome of M.E (ECE) PEC108/109: EMBEDDED SYSTEMS DESIGN 1. Recognize the Embedded system and its programming, Embedded Systems on a Chip (SoC) and the use of VLSI designed circuits. 2. Identify
More informationHardware Neuronale Netzwerke - Lernen durch künstliche Evolution (?)
SKIP - May 2004 Hardware Neuronale Netzwerke - Lernen durch künstliche Evolution (?) S. G. Hohmann, Electronic Vision(s), Kirchhoff Institut für Physik, Universität Heidelberg Hardware Neuronale Netzwerke
More informationA STUDY OF SOME DATA MINING CLASSIFICATION TECHNIQUES
A STUDY OF SOME DATA MINING CLASSIFICATION TECHNIQUES Narsaiah Putta Assistant professor Department of CSE, VASAVI College of Engineering, Hyderabad, Telangana, India Abstract Abstract An Classification
More informationInfrastructure for Autonomous Mobile Robots Communication and Coordination
90 Work in Progress Session Infrastructure for Autonomous Mobile Robots Communication and Coordination Marcelo M. Sobral, Leandro B. Becker Dept of Automation and Systems Universidade Federal de Santa
More informationIMPLEMENTATION OF FPGA-BASED ARTIFICIAL NEURAL NETWORK (ANN) FOR FULL ADDER. Research Scholar, IIT Kharagpur.
Journal of Analysis and Computation (JAC) (An International Peer Reviewed Journal), www.ijaconline.com, ISSN 0973-2861 Volume XI, Issue I, Jan- December 2018 IMPLEMENTATION OF FPGA-BASED ARTIFICIAL NEURAL
More informationISSN: ISO 9001:2008 Certified International Journal of Engineering and Innovative Technology (IJEIT) Volume 3, Issue 1, July 2013
Application of Neural Network for Different Learning Parameter in Classification of Local Feature Image Annie anak Joseph, Chong Yung Fook Universiti Malaysia Sarawak, Faculty of Engineering, 94300, Kota
More informationAutomata Construct with Genetic Algorithm
Automata Construct with Genetic Algorithm Vít Fábera Department of Informatics and Telecommunication, Faculty of Transportation Sciences, Czech Technical University, Konviktská 2, Praha, Czech Republic,
More informationDr. Qadri Hamarsheh Supervised Learning in Neural Networks (Part 1) learning algorithm Δwkj wkj Theoretically practically
Supervised Learning in Neural Networks (Part 1) A prescribed set of well-defined rules for the solution of a learning problem is called a learning algorithm. Variety of learning algorithms are existing,
More informationCMPT 882 Week 3 Summary
CMPT 882 Week 3 Summary! Artificial Neural Networks (ANNs) are networks of interconnected simple units that are based on a greatly simplified model of the brain. ANNs are useful learning tools by being
More informationWorld Journal of Engineering Research and Technology WJERT
wjert, 2019, Vol. 5, Issue 1, 128-138. Original Article ISSN 2454-695X Abigo et al. WJERT www.wjert.org SJIF Impact Factor: 5.218 APPLICATION OF ARTIFICIAL NEURAL NETWORK IN OPTIMIZATION OF SOAP PRODUCTION
More information2. Neural network basics
2. Neural network basics Next commonalities among different neural networks are discussed in order to get started and show which structural parts or concepts appear in almost all networks. It is presented
More informationReservoir Computing for Neural Networks
Reservoir Computing for Neural Networks Felix Grezes CUNY Graduate Center fgrezes@gc.cuny.edu September 4, 2014 Felix Grezes (CUNY) Reservoir Computing September 4, 2014 1 / 33 Introduction The artificial
More informationKernel PCA in nonlinear visualization of a healthy and a faulty planetary gearbox data
Kernel PCA in nonlinear visualization of a healthy and a faulty planetary gearbox data Anna M. Bartkowiak 1, Radoslaw Zimroz 2 1 Wroclaw University, Institute of Computer Science, 50-383, Wroclaw, Poland,
More informationData Mining and Analytics
Data Mining and Analytics Aik Choon Tan, Ph.D. Associate Professor of Bioinformatics Division of Medical Oncology Department of Medicine aikchoon.tan@ucdenver.edu 9/22/2017 http://tanlab.ucdenver.edu/labhomepage/teaching/bsbt6111/
More informationLecture 2 Notes. Outline. Neural Networks. The Big Idea. Architecture. Instructors: Parth Shah, Riju Pahwa
Instructors: Parth Shah, Riju Pahwa Lecture 2 Notes Outline 1. Neural Networks The Big Idea Architecture SGD and Backpropagation 2. Convolutional Neural Networks Intuition Architecture 3. Recurrent Neural
More informationArtificial neural networks are the paradigm of connectionist systems (connectionism vs. symbolism)
Artificial Neural Networks Analogy to biological neural systems, the most robust learning systems we know. Attempt to: Understand natural biological systems through computational modeling. Model intelligent
More informationKnowledge Engineering and Data Mining. Knowledge engineering has 6 basic phases:
Knowledge Engineering and Data Mining Knowledge Engineering The process of building intelligent knowledge based systems is called knowledge engineering Knowledge engineering has 6 basic phases: 1. Problem
More informationCS 4510/9010 Applied Machine Learning
CS 4510/9010 Applied Machine Learning Neural Nets Paula Matuszek Spring, 2015 1 Neural Nets, the very short version A neural net consists of layers of nodes, or neurons, each of which has an activation
More informationINTELLIGENT PROCESS SELECTION FOR NTM - A NEURAL NETWORK APPROACH
International Journal of Industrial Engineering Research and Development (IJIERD), ISSN 0976 6979(Print), ISSN 0976 6987(Online) Volume 1, Number 1, July - Aug (2010), pp. 87-96 IAEME, http://www.iaeme.com/iierd.html
More informationCS 4510/9010 Applied Machine Learning. Neural Nets. Paula Matuszek Fall copyright Paula Matuszek 2016
CS 4510/9010 Applied Machine Learning 1 Neural Nets Paula Matuszek Fall 2016 Neural Nets, the very short version 2 A neural net consists of layers of nodes, or neurons, each of which has an activation
More informationCreating Situational Awareness with Spacecraft Data Trending and Monitoring
Creating Situational Awareness with Spacecraft Data Trending and Monitoring Zhenping Li ASRC Technical Services, Zhenping.Li@asrcfederal.com J.P. Douglas, and Ken Mitchell ASRC Technical Services, JPaul.Douglas@noaa.gov
More informationKeywords: ANN; network topology; bathymetric model; representability.
Proceedings of ninth International Conference on Hydro-Science and Engineering (ICHE 2010), IIT Proceedings Madras, Chennai, of ICHE2010, India. IIT Madras, Aug 2-5,2010 DETERMINATION OF 2 NETWORK - 5
More informationAssignment # 5. Farrukh Jabeen Due Date: November 2, Neural Networks: Backpropation
Farrukh Jabeen Due Date: November 2, 2009. Neural Networks: Backpropation Assignment # 5 The "Backpropagation" method is one of the most popular methods of "learning" by a neural network. Read the class
More informationSeismic regionalization based on an artificial neural network
Seismic regionalization based on an artificial neural network *Jaime García-Pérez 1) and René Riaño 2) 1), 2) Instituto de Ingeniería, UNAM, CU, Coyoacán, México D.F., 014510, Mexico 1) jgap@pumas.ii.unam.mx
More informationIMPLEMENTATION OF RBF TYPE NETWORKS BY SIGMOIDAL FEEDFORWARD NEURAL NETWORKS
IMPLEMENTATION OF RBF TYPE NETWORKS BY SIGMOIDAL FEEDFORWARD NEURAL NETWORKS BOGDAN M.WILAMOWSKI University of Wyoming RICHARD C. JAEGER Auburn University ABSTRACT: It is shown that by introducing special
More informationApplication of Artificial Neural Network for the Inversion of Electrical Resistivity Data
Journal of Informatics and Mathematical Sciences Vol. 9, No. 2, pp. 297 316, 2017 ISSN 0975-5748 (online); 0974-875X (print) Published by RGN Publications http://www.rgnpublications.com Proceedings of
More informationImplementing Sequential Consistency In Cache-Based Systems
To appear in the Proceedings of the 1990 International Conference on Parallel Processing Implementing Sequential Consistency In Cache-Based Systems Sarita V. Adve Mark D. Hill Computer Sciences Department
More informationAutomatic Modularization of ANNs Using Adaptive Critic Method
Automatic Modularization of ANNs Using Adaptive Critic Method RUDOLF JAKŠA Kyushu Institute of Design 4-9-1 Shiobaru, Minami-ku, Fukuoka, 815-8540 JAPAN Abstract: - We propose automatic modularization
More informationImage Compression: An Artificial Neural Network Approach
Image Compression: An Artificial Neural Network Approach Anjana B 1, Mrs Shreeja R 2 1 Department of Computer Science and Engineering, Calicut University, Kuttippuram 2 Department of Computer Science and
More informationOMBP: Optic Modified BackPropagation training algorithm for fast convergence of Feedforward Neural Network
2011 International Conference on Telecommunication Technology and Applications Proc.of CSIT vol.5 (2011) (2011) IACSIT Press, Singapore OMBP: Optic Modified BackPropagation training algorithm for fast
More information1. Introduction. 2. Motivation and Problem Definition. Volume 8 Issue 2, February Susmita Mohapatra
Pattern Recall Analysis of the Hopfield Neural Network with a Genetic Algorithm Susmita Mohapatra Department of Computer Science, Utkal University, India Abstract: This paper is focused on the implementation
More informationArgha Roy* Dept. of CSE Netaji Subhash Engg. College West Bengal, India.
Volume 3, Issue 3, March 2013 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Training Artificial
More informationINSTITUTE OF AERONAUTICAL ENGINEERING (Autonomous) Dundigal, Hyderabad
INSTITUTE OF AERONAUTICAL ENGINEERING (Autonomous) Dundigal, Hyderabad - 500 043 INFORMATION TECHNOLOGY COURSE DESCRIPTION FORM Course Title Course Code Regulation Course Structure Course Coordinator SOFTWARE
More informationCL7204-SOFT COMPUTING TECHNIQUES
VALLIAMMAI ENGINEERING COLLEGE 2015-2016(EVEN) [DOCUMENT TITLE] CL7204-SOFT COMPUTING TECHNIQUES UNIT I Prepared b Ms. Z. Jenifer A. P(O.G) QUESTION BANK INTRODUCTION AND NEURAL NETWORKS 1. What is soft
More informationAN APPROACH FOR LOAD BALANCING FOR SIMULATION IN HETEROGENEOUS DISTRIBUTED SYSTEMS USING SIMULATION DATA MINING
AN APPROACH FOR LOAD BALANCING FOR SIMULATION IN HETEROGENEOUS DISTRIBUTED SYSTEMS USING SIMULATION DATA MINING Irina Bernst, Patrick Bouillon, Jörg Frochte *, Christof Kaufmann Dept. of Electrical Engineering
More informationUtilizing Neural Networks to Reduce Packet Loss in Self-Similar Teletraffic Patterns
Utilizing Neural Networks to Reduce Packet Loss in Self-Similar Teletraffic Patterns Homayoun Yousefi zadeh; EECS Dept; UC, Irvine Edmond A. Jonckheere; EE-Systems Dept; USC John A. Silvester; EE-Systems
More informationLead author L. Pizzol (UNIVE) Report short name WP1_D1.3. Deliverable number D1.3 Due date for deliverable 28/02/2014
TIMBRE Information System for Brownfield Regeneration Lead author L. Pizzol (UNIVE) Report short name WP1_D1.3 Deliverable number D1.3 Due date for deliverable 28/02/2014 Version 3 Actual date for delivery
More informationBipartite Graph Partitioning and Content-based Image Clustering
Bipartite Graph Partitioning and Content-based Image Clustering Guoping Qiu School of Computer Science The University of Nottingham qiu @ cs.nott.ac.uk Abstract This paper presents a method to model the
More informationSaint Petersburg Electrotechnical University "LETI" (ETU "LETI") , Saint Petersburg, Russian FederationProfessoraPopova str.
Saint Petersburg Electrotechnical University "LETI" (ETU "LETI") 197376, Saint Petersburg, Russian FederationProfessoraPopova str., 5 Master s program "Computer Science and Knowledge Discovery" Professor
More informationNEURAL NETWORKS. Typeset by FoilTEX 1
NEURAL NETWORKS Typeset by FoilTEX 1 Basic Concepts The McCulloch-Pitts model Hebb s rule Neural network: double dynamics. Pattern Formation and Pattern Recognition Neural network as an input-output device
More informationAppears in Proceedings of the International Joint Conference on Neural Networks (IJCNN-92), Baltimore, MD, vol. 2, pp. II II-397, June, 1992
Appears in Proceedings of the International Joint Conference on Neural Networks (IJCNN-92), Baltimore, MD, vol. 2, pp. II-392 - II-397, June, 1992 Growing Layers of Perceptrons: Introducing the Extentron
More information11/14/2010 Intelligent Systems and Soft Computing 1
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 informationSemester Wise Schema BS Computer Science
Semester I (Credit Hours: 15) 1 CSC-101 Introduction to Information and Communication Technology (ICT) 4(3 + 1) -NONE- 2 CSC-102 Introduction to Programming 4 (3 + 1) -NONE- 3 ENG-101 Functional English
More informationINTERNATIONAL CIVIL AVIATION ORGANIZATION ASIA and PACIFIC OFFICE ASIA/PAC RECOMMENDED SECURITY CHECKLIST
INTERNATIONAL CIVIL AVIATION ORGANIZATION ASIA and PACIFIC OFFICE Aeronautical Telecommunication Network Implementation Coordination Group (ATNICG) ASIA/PAC RECOMMENDED SECURITY CHECKLIST September 2009
More informationWHAT TYPE OF NEURAL NETWORK IS IDEAL FOR PREDICTIONS OF SOLAR FLARES?
WHAT TYPE OF NEURAL NETWORK IS IDEAL FOR PREDICTIONS OF SOLAR FLARES? Initially considered for this model was a feed forward neural network. Essentially, this means connections between units do not form
More information