Neural Networks. Hervé Abdi. The University of Texas at Dallas
|
|
- Austen Strickland
- 7 years ago
- Views:
Transcription
1 Neural Netorks. Hervé Abd The Unversty o Texas at Dallas Introducton Neural netorks are adaptve statstcal models based on an analogy th the structure o the bran. They are adaptve because they can learn to estmate the parameters o some populaton usng a small number o exemplars (one or a e) at a tme. They do not der essentally rom standard statstcal models. For example, one can nd neural netork archtectures akn to dscrmnant analyss, prncpal component analyss, logstc regresson, and other technques. In act, the same mathematcal tools can be used to analyze standard statstcal models and neural netorks. Neural netorks are used as statstcal tools n a varety o elds, ncludng psychology, statstcs, engneerng, econometrcs, and even physcs. They are used also as models o cogntve processes by neuro- and cogntve scentsts. Bascally, neural netorks are bult rom smple unts, sometmes called neurons or cells by analogy th the real thng. These unts are lnked by a set o eghted connectons. Learnng s usually accomplshed by modcaton o the connecton eghts. Each unt codes or corresponds to a eature or a characterstc o a pattern that e ant to analyze or that e ant to use as a predctor. These netorks usually organze ther unts nto several layers. The rst layer s called the nput layer, the last one the output layer. The ntermedate layers ( any) are called the hdden layers. The normaton to be analyzed s ed to the neurons o the rst layer and then propagated to the neurons o the second layer or urther processng. The result o ths processng s then propagated to the next layer and so on untl the last layer. Each unt receves some normaton rom other unts (or rom the external orld through some devces) and processes ths normaton, hch ll be converted nto the output o the unt. The goal o the netork s to learn or to dscover some assocaton beteen nput and output patterns, or to analyze, or to nd the structure o the nput patterns. The learnng process s acheved through the modcaton o the connecton eghts beteen unts. In statstcal terms, ths s equvalent to In: Les-Beck M., Bryman, A., Futng T. (Eds.) (2003). Encyclopeda o Socal Scences Research Methods. Thousand Oaks (CA): Sage. Address correspondence to Hervé Abd Program n Cognton and Neuroscences, MS: Gr.4., The Unversty o Texas at Dallas, Rchardson, TX , USA E-mal: herve@utdallas.edu herve
2 nterpretng the value o the connectons beteen unts as parameters (e.g., lke the values o a and b n the regresson equaton ŷ = a + bx) to be estmated. The learnng process speces the algorthm used to estmate the parameters. The buldng blocks o neural netorks Neural netorks are made o basc unts (see Fgure ) arranged n layers. A unt collects normaton provded by other unts (or by the external orld) to hch t s connected th eghted connectons called synapses. These eghts, called synaptc eghts multply (.e., amply or attenuate) the nput normaton: A postve eght s consdered exctatory, a negatve eght nhbtory. x Bas cell x 0 = Input x I a =Σ 0 x = θ a (a) Output x I Computaton o the actvaton Transormaton o the actvaton The Basc Neural Unt Fgure : The basc neural unt processes the nput normaton nto the output normaton. Each o these unts s a smpled model o a neuron and transorms ts nput normaton nto an output response. Ths transormaton nvolves to steps: Frst, the actvaton o the neuron s computed as the eghted sum o t nputs, and second ths actvaton s transormed nto a response by usng a transer uncton. Formally, each nput s denoted x, and each eght, then the actvaton s equal to a = x, and the output denoted o s obtaned as o = (a). Any uncton hose doman s the real numbers can be used as a transer uncton. The most popular ones are the lnear uncton (o a), the step uncton (actvaton values less than a gven threshold [ are set to 0 or to ] and the other values are set to +), the logstc uncton (x) = + exp{ x} hch maps the real numbers nto the nterval [ + ] and hose dervatve, needed or learnng, s easly computed { (x) = (x)[ (x)]}, and the normal or Gaussan uncton [o = (σ 2π) exp{ 2 (a/σ)2 }]. Some o these unctons can nclude probablstc varatons; or example, a neuron can transorm ts actvaton nto the response + th a probablty o 2 hen the actvaton s larger than a gven threshold. 2
3 The archtecture (.e., the pattern o connectvty) o the netork, along th the transer unctons used by the neurons and the synaptc eghts, completely specy the behavor o the netork. Learnng rules Neural netorks are adaptve statstcal devces. Ths means that they can change teratvely the values o ther parameters (.e., the synaptc eghts) as a uncton o ther perormance. These changes are made accordng to learnng rules hch can be characterzed as supervsed (hen a desred output s knon and used to compute an error sgnal) or unsupervsed (hen no such error sgnal s used). The Wdro-Ho (a.k.a., gradent descent or Delta rule) s the most dely knon supervsed learnng rule. It uses the derence beteen the actual nput o the cell and the desred output as an error sgnal or unts n the output layer. Unts n the hdden layers cannot compute drectly ther error sgnal but estmate t as a uncton (e.g., a eghted average) o the error o the unts n the ollong layer. Ths adaptaton o the Wdro-Ho learnng rule s knon as error backpropagaton. Wth Wdro-Ho learnng, the correcton to the synaptc eghts s proportonal to the error sgnal multpled by the value o the actvaton gven by the dervatve o the transer uncton. Usng the dervatve has the eect o makng nely tuned correctons hen the actvaton s near ts extreme values (mnmum or maxmum) and larger correctons hen the actvaton s n ts mddle range. Each correcton has the mmedate eect o makng the error sgnal smaller a smlar nput s appled to the unt. In general, supervsed learnng rules mplement optmzaton algorthms akn to descent technques because they search or a set o values or the ree parameters (.e., the synaptc eghts) o the system such that some error uncton computed or the hole netork s mnmzed. The Hebban rule s the most dely knon unsupervsed learnng rule, t s based on ork by the Canadan neuropsychologst Donald Hebb, ho theorzed that neuronal learnng (.e., synaptc change) s a local phenomenon expressble n terms o the temporal correlaton beteen the actvaton values o neurons. Speccally, the synaptc change depends on both presynaptc and postsynaptc actvtes and states that the change n a synaptc eght s a uncton o the temporal correlaton beteen the presynaptc and postsynaptc actvtes. Speccally, the value o the synaptc eght beteen to neurons ncreases henever they are n the same state and decreases hen they are n derent states. Some mportant neural netork archtecture One the most popular archtectures n neural netorks s the mult-layer perceptron (see Fgure 2). Most o the netorks th ths archtecture use the Wdro-Ho rule as ther learnng algorthm and the logstc uncton as the transer uncton o the unts o the hdden layer (the transer uncton s n general non-lnear or these neurons). These netorks are very popular because they can approxmate any multvarate uncton relatng the nput to the 3
4 output. In a statstcal rameork, these netorks are akn to multvarate non-lnear regresson. When the nput patterns are the same are the output patterns, these netorks are called auto-assocators. They are closely related to lnear ( the hdden unts are lnear) or non-lnear ( not) prncpal component analyss and other statstcal technques lnked to the general lnear model (see Abd et al., 996), such as dscrmnant analyss or correspondence analyss. Input Output pattern pattern Input layer Hdden layer Output layer Fgure 2: A mult-layer perceptron. A recent development generalzes the radal bass uncton netorks (rb) (see Abd, Valentn, & Edelman, 999) and ntegrates them th statstcal learnng theory (see Vapnk, 999) under the name o support vector machne or SVM (see Schölkop & Smola, 2003). In these netorks, the hdden unts (called the support vectors) represent possble (or even real) nput patterns and ther response s a uncton to ther smlarty to the nput pattern under consderaton. The smlarty s evaluated by a kernel uncton (e.g., dot product; n the radal bass uncton the kernel s the Gaussan transormaton o the Eucldean dstance beteen the support vector and the nput). In the specc case o rb netorks that e ll use as an example o SVM the output o the unts o the hdden layers are connected to an output layer composed o lnear unts. In act, these netorks ork by breakng the dcult problem o a nonlnear approxmaton nto to more smple ones. The rst step s a smple nonlnear mappng (the Gaussan transormaton o the dstance rom the kernel to the nput pattern), the second step corresponds to a lnear transormaton rom the hdden layer to the output layer. Learnng occurs at the level o the output layer. The man dculty th these archtectures resdes n the choce o the support vectors and the specc kernels to use. These netorks are used or pattern recognton, classcaton, and or clusterng data. Valdaton From a statstcal pont a ve, neural netorks represent a class o nonparametrc adaptve models. In ths rameork, an mportant ssue s to evaluate the perormance o the model. Ths s done by separatng the data nto to sets: the tranng set and the testng set. The parameters (.e., the value o the synaptc eghts) o the netork are computed usng the tranng set. Then 4
5 learnng s stopped and the netork s evaluated th the data rom the testng set. Ths cross-valdaton approach s akn to the bootstrap or the jackkne. Useul reerences Neural netorks theory connects several domans rom the neuroscences to engneerng ncludng statstcal theory. Ths dversty o sources creates also a real heterogenety n the presentaton o the materal as textbooks oten try to address only one porton o the nterested readershp. The ollong reerences should be o nterest or the reader nterested n the statstcal propertes o neural netorks: Abd et al. (999), Bshop (995), Cherkassky and Muler (998), Duda, Hart & Stork (200), Haste, Tbshran, & Fredman (2002), Looney (997), Rpley (996), and Vapnk (999). *Reerences [] Abd, H., Valentn, D., & Edelman, B. (999). Neural netorks. Thousand Oaks (CA): Sage. [2] Abd, H., Valentn, D., Edelman, B., O Toole. A.J. (996). A Wdro-Ho learnng rule or a generalzaton o the lnear auto-assocator. Journal o Mathematcal Psychology, 40, [3] Bshop, C. M. (995) Neural netorks or pattern recognton. Oxord, UK: Oxord Unversty Press. [4] Cherkassky, V., & Muler, F. (998). Learnng rom data. Ne York: Wley. [5] Duda, R., Hart, P.E., Stork, D.G. (200) Pattern classcaton. Ne York: Wley. [6] Haste T., Tbshran R., Fredman J. (200). The elements o statstcal learnng. Ne-Yrok: Sprnger-Verlag [7] Rpley, B.D. (996) Pattern recognton and neural netorks. Cambrdge, MA: Cambrdge Unversty Press. [8] Schölkop B., Smola, A.J. (2003). learnng th kernels. Cambrdge (MA): MIT Press. [9] Vapnk, V. N. (999) Statstcal learnng theory. Ne York: Wley. 5
Lecture 2: Single Layer Perceptrons Kevin Swingler
Lecture 2: Sngle Layer Perceptrons Kevn Sngler kms@cs.str.ac.uk Recap: McCulloch-Ptts Neuron Ths vastly smplfed model of real neurons s also knon as a Threshold Logc Unt: W 2 A Y 3 n W n. A set of synapses
More informationForecasting the Direction and Strength of Stock Market Movement
Forecastng the Drecton and Strength of Stock Market Movement Jngwe Chen Mng Chen Nan Ye cjngwe@stanford.edu mchen5@stanford.edu nanye@stanford.edu Abstract - Stock market s one of the most complcated systems
More informationForecasting the Demand of Emergency Supplies: Based on the CBR Theory and BP Neural Network
700 Proceedngs of the 8th Internatonal Conference on Innovaton & Management Forecastng the Demand of Emergency Supples: Based on the CBR Theory and BP Neural Network Fu Deqang, Lu Yun, L Changbng School
More informationWhat is Candidate Sampling
What s Canddate Samplng Say we have a multclass or mult label problem where each tranng example ( x, T ) conssts of a context x a small (mult)set of target classes T out of a large unverse L of possble
More informationGeorey E. Hinton. University oftoronto. Email: zoubin@cs.toronto.edu. Technical Report CRG-TR-96-1. May 21, 1996 (revised Feb 27, 1997) Abstract
The EM Algorthm for Mxtures of Factor Analyzers Zoubn Ghahraman Georey E. Hnton Department of Computer Scence Unversty oftoronto 6 Kng's College Road Toronto, Canada M5S A4 Emal: zoubn@cs.toronto.edu Techncal
More informationModelling of Web Domain Visits by Radial Basis Function Neural Networks and Support Vector Machine Regression
Modellng of Web Doman Vsts by Radal Bass Functon Neural Networks and Support Vector Machne Regresson Vladmír Olej, Jana Flpová Insttute of System Engneerng and Informatcs Faculty of Economcs and Admnstraton,
More informationLogistic Regression. Lecture 4: More classifiers and classes. Logistic regression. Adaboost. Optimization. Multiple class classification
Lecture 4: More classfers and classes C4B Machne Learnng Hlary 20 A. Zsserman Logstc regresson Loss functons revsted Adaboost Loss functons revsted Optmzaton Multple class classfcaton Logstc Regresson
More informationThe Development of Web Log Mining Based on Improve-K-Means Clustering Analysis
The Development of Web Log Mnng Based on Improve-K-Means Clusterng Analyss TngZhong Wang * College of Informaton Technology, Luoyang Normal Unversty, Luoyang, 471022, Chna wangtngzhong2@sna.cn Abstract.
More informationCausal, Explanatory Forecasting. Analysis. Regression Analysis. Simple Linear Regression. Which is Independent? Forecasting
Causal, Explanatory Forecastng Assumes cause-and-effect relatonshp between system nputs and ts output Forecastng wth Regresson Analyss Rchard S. Barr Inputs System Cause + Effect Relatonshp The job of
More informationL10: Linear discriminants analysis
L0: Lnear dscrmnants analyss Lnear dscrmnant analyss, two classes Lnear dscrmnant analyss, C classes LDA vs. PCA Lmtatons of LDA Varants of LDA Other dmensonalty reducton methods CSCE 666 Pattern Analyss
More informationFigure 1. Training and Test data sets for Nasdaq-100 Index (b) NIFTY index
Modelng Chaotc Behavor of Stock Indces Usng Intellgent Paradgms Ajth Abraham, Nnan Sajth Phlp and P. Saratchandran Department of Computer Scence, Oklahoma State Unversty, ulsa, Oklahoma 746, USA, Emal:
More informationCS 2750 Machine Learning. Lecture 3. Density estimation. CS 2750 Machine Learning. Announcements
Lecture 3 Densty estmaton Mlos Hauskrecht mlos@cs.ptt.edu 5329 Sennott Square Next lecture: Matlab tutoral Announcements Rules for attendng the class: Regstered for credt Regstered for audt (only f there
More informationSingle and multiple stage classifiers implementing logistic discrimination
Sngle and multple stage classfers mplementng logstc dscrmnaton Hélo Radke Bttencourt 1 Dens Alter de Olvera Moraes 2 Vctor Haertel 2 1 Pontfíca Unversdade Católca do Ro Grande do Sul - PUCRS Av. Ipranga,
More informationAn artificial Neural Network approach to monitor and diagnose multi-attribute quality control processes. S. T. A. Niaki*
Journal of Industral Engneerng Internatonal July 008, Vol. 4, No. 7, 04 Islamc Azad Unversty, South Tehran Branch An artfcal Neural Network approach to montor and dagnose multattrbute qualty control processes
More informationA study on the ability of Support Vector Regression and Neural Networks to Forecast Basic Time Series Patterns
A study on the ablty of Support Vector Regresson and Neural Networks to Forecast Basc Tme Seres Patterns Sven F. Crone, Jose Guajardo 2, and Rchard Weber 2 Lancaster Unversty, Department of Management
More informationSorting Online Reviews by Usefulness Based on the VIKOR Method
Assocaton or Inormaton Systems AIS Electronc Lbrary (AISeL) Eleventh Wuhan Internatonal Conerence on e- Busness Wuhan Internatonal Conerence on e-busness 5-26-2012 Sortng Onlne Revews by Useulness Based
More informationSmart Home Security System Based on ANFIS
Smart Home Securty System Based on ANFIS LeeJeong-G 1,Lee Sang-Hyun 2, Moon Kyung-Il 2 1 Korea Electroncs Technology Insttute, Korea 2 Dept. o Computer Engneerng, Honam Unversty, Korea 2 Dept. o Computer
More informationTime Delayed Independent Component Analysis for Data Quality Monitoring
IWSSIP 1-17th Internatonal Conference on Systems, Sgnals and Image Processng Tme Delayed Independent Component Analyss for Data Qualty Montorng José Márco Faer Sgnal Processng Laboratory, COE/Pol Federal
More informationAn Efficient and Simplified Model for Forecasting using SRM
HAFIZ MUHAMMAD SHAHZAD ASIF*, MUHAMMAD FAISAL HAYAT*, AND TAUQIR AHMAD* RECEIVED ON 15.04.013 ACCEPTED ON 09.01.014 ABSTRACT Learnng form contnuous fnancal systems play a vtal role n enterprse operatons.
More informationPerformance Analysis of Energy Consumption of Smartphone Running Mobile Hotspot Application
Internatonal Journal of mart Grd and lean Energy Performance Analyss of Energy onsumpton of martphone Runnng Moble Hotspot Applcaton Yun on hung a chool of Electronc Engneerng, oongsl Unversty, 511 angdo-dong,
More informationVision Mouse. Saurabh Sarkar a* University of Cincinnati, Cincinnati, USA ABSTRACT 1. INTRODUCTION
Vson Mouse Saurabh Sarkar a* a Unversty of Cncnnat, Cncnnat, USA ABSTRACT The report dscusses a vson based approach towards trackng of eyes and fngers. The report descrbes the process of locatng the possble
More informationAn Interest-Oriented Network Evolution Mechanism for Online Communities
An Interest-Orented Network Evoluton Mechansm for Onlne Communtes Cahong Sun and Xaopng Yang School of Informaton, Renmn Unversty of Chna, Bejng 100872, P.R. Chna {chsun,yang}@ruc.edu.cn Abstract. Onlne
More informationCHAPTER 5 RELATIONSHIPS BETWEEN QUANTITATIVE VARIABLES
CHAPTER 5 RELATIONSHIPS BETWEEN QUANTITATIVE VARIABLES In ths chapter, we wll learn how to descrbe the relatonshp between two quanttatve varables. Remember (from Chapter 2) that the terms quanttatve varable
More informationPerformance Analysis and Coding Strategy of ECOC SVMs
Internatonal Journal of Grd and Dstrbuted Computng Vol.7, No. (04), pp.67-76 http://dx.do.org/0.457/jgdc.04.7..07 Performance Analyss and Codng Strategy of ECOC SVMs Zhgang Yan, and Yuanxuan Yang, School
More informationProject Networks With Mixed-Time Constraints
Project Networs Wth Mxed-Tme Constrants L Caccetta and B Wattananon Western Australan Centre of Excellence n Industral Optmsaton (WACEIO) Curtn Unversty of Technology GPO Box U1987 Perth Western Australa
More informationChapter 6. Classification and Prediction
Chapter 6. Classfcaton and Predcton What s classfcaton? What s Lazy learners (or learnng from predcton? your neghbors) Issues regardng classfcaton and Frequent-pattern-based predcton classfcaton Classfcaton
More informationCHAPTER 14 MORE ABOUT REGRESSION
CHAPTER 14 MORE ABOUT REGRESSION We learned n Chapter 5 that often a straght lne descrbes the pattern of a relatonshp between two quanttatve varables. For nstance, n Example 5.1 we explored the relatonshp
More informationBiometric Signature Processing & Recognition Using Radial Basis Function Network
Bometrc Sgnature Processng & Recognton Usng Radal Bass Functon Network Ankt Chadha, Neha Satam, and Vbha Wal Abstract- Automatc recognton of sgnature s a challengng problem whch has receved much attenton
More informationHow To Know The Components Of Mean Squared Error Of Herarchcal Estmator S
S C H E D A E I N F O R M A T I C A E VOLUME 0 0 On Mean Squared Error of Herarchcal Estmator Stans law Brodowsk Faculty of Physcs, Astronomy, and Appled Computer Scence, Jagellonan Unversty, Reymonta
More informationProbabilistic Linear Classifier: Logistic Regression. CS534-Machine Learning
robablstc Lnear Classfer: Logstc Regresson CS534-Machne Learnng Three Man Approaches to learnng a Classfer Learn a classfer: a functon f, ŷ f Learn a probablstc dscrmnatve model,.e., the condtonal dstrbuton
More informationModule 2 LOSSLESS IMAGE COMPRESSION SYSTEMS. Version 2 ECE IIT, Kharagpur
Module LOSSLESS IMAGE COMPRESSION SYSTEMS Lesson 3 Lossless Compresson: Huffman Codng Instructonal Objectves At the end of ths lesson, the students should be able to:. Defne and measure source entropy..
More informationOn-Line Fault Detection in Wind Turbine Transmission System using Adaptive Filter and Robust Statistical Features
On-Lne Fault Detecton n Wnd Turbne Transmsson System usng Adaptve Flter and Robust Statstcal Features Ruoyu L Remote Dagnostcs Center SKF USA Inc. 3443 N. Sam Houston Pkwy., Houston TX 77086 Emal: ruoyu.l@skf.com
More informationOffline Verification of Hand Written Signature using Adaptive Resonance Theory Net (Type-1)
Internatonal Journal of Sgnal Processng Systems Vol, No June 203 Offlne Verfcaton of Hand Wrtten Sgnature usng Adaptve Resonance Theory Net (Type-) Trtharaj Dash Veer Surendra Sa Unversty of Technology,
More informationBERNSTEIN POLYNOMIALS
On-Lne Geometrc Modelng Notes BERNSTEIN POLYNOMIALS Kenneth I. Joy Vsualzaton and Graphcs Research Group Department of Computer Scence Unversty of Calforna, Davs Overvew Polynomals are ncredbly useful
More informationA DATA MINING APPLICATION IN A STUDENT DATABASE
JOURNAL OF AERONAUTICS AND SPACE TECHNOLOGIES JULY 005 VOLUME NUMBER (53-57) A DATA MINING APPLICATION IN A STUDENT DATABASE Şenol Zafer ERDOĞAN Maltepe Ünversty Faculty of Engneerng Büyükbakkalköy-Istanbul
More informationNPAR TESTS. One-Sample Chi-Square Test. Cell Specification. Observed Frequencies 1O i 6. Expected Frequencies 1EXP i 6
PAR TESTS If a WEIGHT varable s specfed, t s used to replcate a case as many tmes as ndcated by the weght value rounded to the nearest nteger. If the workspace requrements are exceeded and samplng has
More informationECE544NA Final Project: Robust Machine Learning Hardware via Classifier Ensemble
1 ECE544NA Fnal Project: Robust Machne Learnng Hardware va Classfer Ensemble Sa Zhang, szhang12@llnos.edu Dept. of Electr. & Comput. Eng., Unv. of Illnos at Urbana-Champagn, Urbana, IL, USA Abstract In
More informationTHE APPLICATION OF DATA MINING TECHNIQUES AND MULTIPLE CLASSIFIERS TO MARKETING DECISION
Internatonal Journal of Electronc Busness Management, Vol. 3, No. 4, pp. 30-30 (2005) 30 THE APPLICATION OF DATA MINING TECHNIQUES AND MULTIPLE CLASSIFIERS TO MARKETING DECISION Yu-Mn Chang *, Yu-Cheh
More information8.5 UNITARY AND HERMITIAN MATRICES. The conjugate transpose of a complex matrix A, denoted by A*, is given by
6 CHAPTER 8 COMPLEX VECTOR SPACES 5. Fnd the kernel of the lnear transformaton gven n Exercse 5. In Exercses 55 and 56, fnd the mage of v, for the ndcated composton, where and are gven by the followng
More informationA FEATURE SELECTION AGENT-BASED IDS
A FEATURE SELECTION AGENT-BASED IDS Emlo Corchado, Álvaro Herrero and José Manuel Sáz Department of Cvl Engneerng, Unversty of Burgos C/Francsco de Vtora s/n., 09006, Burgos, Span Phone: +34 947259395,
More informationMATHEMATICAL ENGINEERING TECHNICAL REPORTS. Sequential Optimizing Investing Strategy with Neural Networks
MATHEMATICAL ENGINEERING TECHNICAL REPORTS Sequental Optmzng Investng Strategy wth Neural Networks Ryo ADACHI and Akmch TAKEMURA METR 2010 03 February 2010 DEPARTMENT OF MATHEMATICAL INFORMATICS GRADUATE
More informationFuzzy Regression and the Term Structure of Interest Rates Revisited
Fuzzy Regresson and the Term Structure of Interest Rates Revsted Arnold F. Shapro Penn State Unversty Smeal College of Busness, Unversty Park, PA 68, USA Phone: -84-865-396, Fax: -84-865-684, E-mal: afs@psu.edu
More informationFaraday's Law of Induction
Introducton Faraday's Law o Inducton In ths lab, you wll study Faraday's Law o nducton usng a wand wth col whch swngs through a magnetc eld. You wll also examne converson o mechanc energy nto electrc energy
More informationA cooperative connectionist IDS model to identify independent anomalous SNMP situations
A cooperatve connectonst IDS model to dentfy ndependent anomalous SNMP stuatons Álvaro Herrero, Emlo Corchado, José Manuel Sáz Department of Cvl Engneerng, Unversty of Burgos, Span escorchado@ubu.es Abstract
More informationExample-based head tracking
MITSUBISHI ELECTRIC RESEARCH LABORATORIES http://www.merl.com Example-based head trackng S. Nyog TR96-34 December 1996 Abstract We want to estmate the pose of human heads. Ths estmaton nvolves a nonlnear
More informationStatistical Methods to Develop Rating Models
Statstcal Methods to Develop Ratng Models [Evelyn Hayden and Danel Porath, Österrechsche Natonalbank and Unversty of Appled Scences at Manz] Source: The Basel II Rsk Parameters Estmaton, Valdaton, and
More informationTHE METHOD OF LEAST SQUARES THE METHOD OF LEAST SQUARES
The goal: to measure (determne) an unknown quantty x (the value of a RV X) Realsaton: n results: y 1, y 2,..., y j,..., y n, (the measured values of Y 1, Y 2,..., Y j,..., Y n ) every result s encumbered
More informationFinancial market forecasting using a two-step kernel learning method for the support vector regression
Ann Oper Res (2010) 174: 103 120 DOI 10.1007/s10479-008-0357-7 Fnancal market forecastng usng a two-step kernel learnng method for the support vector regresson L Wang J Zhu Publshed onlne: 28 May 2008
More informationA hybrid global optimization algorithm based on parallel chaos optimization and outlook algorithm
Avalable onlne www.ocpr.com Journal of Chemcal and Pharmaceutcal Research, 2014, 6(7):1884-1889 Research Artcle ISSN : 0975-7384 CODEN(USA) : JCPRC5 A hybrd global optmzaton algorthm based on parallel
More informationFeature selection for intrusion detection. Slobodan Petrović NISlab, Gjøvik University College
Feature selecton for ntruson detecton Slobodan Petrovć NISlab, Gjøvk Unversty College Contents The feature selecton problem Intruson detecton Traffc features relevant for IDS The CFS measure The mrmr measure
More informationPerformance attribution for multi-layered investment decisions
Performance attrbuton for mult-layered nvestment decsons 880 Thrd Avenue 7th Floor Ne Yor, NY 10022 212.866.9200 t 212.866.9201 f qsnvestors.com Inna Oounova Head of Strategc Asset Allocaton Portfolo Management
More informationSupport Vector Machines
Support Vector Machnes Max Wellng Department of Computer Scence Unversty of Toronto 10 Kng s College Road Toronto, M5S 3G5 Canada wellng@cs.toronto.edu Abstract Ths s a note to explan support vector machnes.
More informationOut-of-Sample Extensions for LLE, Isomap, MDS, Eigenmaps, and Spectral Clustering
Out-of-Sample Extensons for LLE, Isomap, MDS, Egenmaps, and Spectral Clusterng Yoshua Bengo, Jean-Franços Paement, Pascal Vncent Olver Delalleau, Ncolas Le Roux and Mare Oumet Département d Informatque
More informationImplementation of Deutsch's Algorithm Using Mathcad
Implementaton of Deutsch's Algorthm Usng Mathcad Frank Roux The followng s a Mathcad mplementaton of Davd Deutsch's quantum computer prototype as presented on pages - n "Machnes, Logc and Quantum Physcs"
More informationAUTHENTICATION OF OTTOMAN ART CALLIGRAPHERS
INTERNATIONAL JOURNAL OF ELECTRONICS; MECHANICAL and MECHATRONICS ENGINEERING Vol.2 Num.2 pp.(2-22) AUTHENTICATION OF OTTOMAN ART CALLIGRAPHERS Osman N. Ucan Mustafa Istanbullu Nyaz Klc2 Ahmet Kala3 Istanbul
More informationForecasting and Modelling Electricity Demand Using Anfis Predictor
Journal of Mathematcs and Statstcs 7 (4): 75-8, 0 ISSN 549-3644 0 Scence Publcatons Forecastng and Modellng Electrcty Demand Usng Anfs Predctor M. Mordjaou and B. Boudjema Department of Electrcal Engneerng,
More informationFace Verification Problem. Face Recognition Problem. Application: Access Control. Biometric Authentication. Face Verification (1:1 matching)
Face Recognton Problem Face Verfcaton Problem Face Verfcaton (1:1 matchng) Querymage face query Face Recognton (1:N matchng) database Applcaton: Access Control www.vsage.com www.vsoncs.com Bometrc Authentcaton
More information1. Measuring association using correlation and regression
How to measure assocaton I: Correlaton. 1. Measurng assocaton usng correlaton and regresson We often would lke to know how one varable, such as a mother's weght, s related to another varable, such as a
More informationData Visualization by Pairwise Distortion Minimization
Communcatons n Statstcs, Theory and Methods 34 (6), 005 Data Vsualzaton by Parwse Dstorton Mnmzaton By Marc Sobel, and Longn Jan Lateck* Department of Statstcs and Department of Computer and Informaton
More informationProperties of Indoor Received Signal Strength for WLAN Location Fingerprinting
Propertes of Indoor Receved Sgnal Strength for WLAN Locaton Fngerprntng Kamol Kaemarungs and Prashant Krshnamurthy Telecommuncatons Program, School of Informaton Scences, Unversty of Pttsburgh E-mal: kakst2,prashk@ptt.edu
More informationGender Classification for Real-Time Audience Analysis System
Gender Classfcaton for Real-Tme Audence Analyss System Vladmr Khryashchev, Lev Shmaglt, Andrey Shemyakov, Anton Lebedev Yaroslavl State Unversty Yaroslavl, Russa vhr@yandex.ru, shmaglt_lev@yahoo.com, andrey.shemakov@gmal.com,
More informationA Genetic Programming Based Stock Price Predictor together with Mean-Variance Based Sell/Buy Actions
Proceedngs of the World Congress on Engneerng 28 Vol II WCE 28, July 2-4, 28, London, U.K. A Genetc Programmng Based Stock Prce Predctor together wth Mean-Varance Based Sell/Buy Actons Ramn Rajaboun and
More informationLecture 5,6 Linear Methods for Classification. Summary
Lecture 5,6 Lnear Methods for Classfcaton Rce ELEC 697 Farnaz Koushanfar Fall 2006 Summary Bayes Classfers Lnear Classfers Lnear regresson of an ndcator matrx Lnear dscrmnant analyss (LDA) Logstc regresson
More informationEstimating the Number of Clusters in Genetics of Acute Lymphoblastic Leukemia Data
Journal of Al Azhar Unversty-Gaza (Natural Scences), 2011, 13 : 109-118 Estmatng the Number of Clusters n Genetcs of Acute Lymphoblastc Leukema Data Mahmoud K. Okasha, Khaled I.A. Almghar Department of
More informationIntra-day Trading of the FTSE-100 Futures Contract Using Neural Networks With Wavelet Encodings
Submtted to European Journal of Fnance Intra-day Tradng of the FTSE-00 Futures Contract Usng eural etworks Wth Wavelet Encodngs D L Toulson S P Toulson Intellgent Fnancal Systems Lmted Sute 4 Greener House
More informationA COLLABORATIVE TRADING MODEL BY SUPPORT VECTOR REGRESSION AND TS FUZZY RULE FOR DAILY STOCK TURNING POINTS DETECTION
A COLLABORATIVE TRADING MODEL BY SUPPORT VECTOR REGRESSION AND TS FUZZY RULE FOR DAILY STOCK TURNING POINTS DETECTION JHENG-LONG WU, PEI-CHANN CHANG, KAI-TING CHANG Department of Informaton Management,
More informationSupport vector domain description
Pattern Recognton Letters 20 (1999) 1191±1199 www.elsever.nl/locate/patrec Support vector doman descrpton Davd M.J. Tax *,1, Robert P.W. Dun Pattern Recognton Group, Faculty of Appled Scence, Delft Unversty
More informationA DYNAMIC CRASHING METHOD FOR PROJECT MANAGEMENT USING SIMULATION-BASED OPTIMIZATION. Michael E. Kuhl Radhamés A. Tolentino-Peña
Proceedngs of the 2008 Wnter Smulaton Conference S. J. Mason, R. R. Hll, L. Mönch, O. Rose, T. Jefferson, J. W. Fowler eds. A DYNAMIC CRASHING METHOD FOR PROJECT MANAGEMENT USING SIMULATION-BASED OPTIMIZATION
More informationLogistic Regression. Steve Kroon
Logstc Regresson Steve Kroon Course notes sectons: 24.3-24.4 Dsclamer: these notes do not explctly ndcate whether values are vectors or scalars, but expects the reader to dscern ths from the context. Scenaro
More informationBANKRUPTCY PREDICTION BY USING SUPPORT VECTOR MACHINES AND GENETIC ALGORITHMS
BANKRUPCY PREDICION BY USING SUPPOR VECOR MACHINES AND GENEIC ALGORIHMS SALEHI Mahd Ferdows Unversty of Mashhad, Iran ROSAMI Neda Islamc Azad Unversty Scence and Research Khorasan-e-Razav Branch Abstract:
More informationANALYZING THE RELATIONSHIPS BETWEEN QUALITY, TIME, AND COST IN PROJECT MANAGEMENT DECISION MAKING
ANALYZING THE RELATIONSHIPS BETWEEN QUALITY, TIME, AND COST IN PROJECT MANAGEMENT DECISION MAKING Matthew J. Lberatore, Department of Management and Operatons, Vllanova Unversty, Vllanova, PA 19085, 610-519-4390,
More informationRESEARCH ON DUAL-SHAKER SINE VIBRATION CONTROL. Yaoqi FENG 1, Hanping QIU 1. China Academy of Space Technology (CAST) yaoqi.feng@yahoo.
ICSV4 Carns Australa 9- July, 007 RESEARCH ON DUAL-SHAKER SINE VIBRATION CONTROL Yaoq FENG, Hanpng QIU Dynamc Test Laboratory, BISEE Chna Academy of Space Technology (CAST) yaoq.feng@yahoo.com Abstract
More informationEfficient Project Portfolio as a tool for Enterprise Risk Management
Effcent Proect Portfolo as a tool for Enterprse Rsk Management Valentn O. Nkonov Ural State Techncal Unversty Growth Traectory Consultng Company January 5, 27 Effcent Proect Portfolo as a tool for Enterprse
More informationDiscussion Papers. Support Vector Machines (SVM) as a Technique for Solvency Analysis. Laura Auria Rouslan A. Moro. Berlin, August 2008
Deutsches Insttut für Wrtschaftsforschung www.dw.de Dscusson Papers 8 Laura Aura Rouslan A. Moro Support Vector Machnes (SVM) as a Technque for Solvency Analyss Berln, August 2008 Opnons expressed n ths
More informationFrequency Selective IQ Phase and IQ Amplitude Imbalance Adjustments for OFDM Direct Conversion Transmitters
Frequency Selectve IQ Phase and IQ Ampltude Imbalance Adjustments for OFDM Drect Converson ransmtters Edmund Coersmeer, Ernst Zelnsk Noka, Meesmannstrasse 103, 44807 Bochum, Germany edmund.coersmeer@noka.com,
More informationCourse outline. Financial Time Series Analysis. Overview. Data analysis. Predictive signal. Trading strategy
Fnancal Tme Seres Analyss Patrck McSharry patrck@mcsharry.net www.mcsharry.net Trnty Term 2014 Mathematcal Insttute Unversty of Oxford Course outlne 1. Data analyss, probablty, correlatons, vsualsaton
More informationCan Auto Liability Insurance Purchases Signal Risk Attitude?
Internatonal Journal of Busness and Economcs, 2011, Vol. 10, No. 2, 159-164 Can Auto Lablty Insurance Purchases Sgnal Rsk Atttude? Chu-Shu L Department of Internatonal Busness, Asa Unversty, Tawan Sheng-Chang
More informationPower-of-Two Policies for Single- Warehouse Multi-Retailer Inventory Systems with Order Frequency Discounts
Power-of-wo Polces for Sngle- Warehouse Mult-Retaler Inventory Systems wth Order Frequency Dscounts José A. Ventura Pennsylvana State Unversty (USA) Yale. Herer echnon Israel Insttute of echnology (Israel)
More informationSIMPLE LINEAR CORRELATION
SIMPLE LINEAR CORRELATION Smple lnear correlaton s a measure of the degree to whch two varables vary together, or a measure of the ntensty of the assocaton between two varables. Correlaton often s abused.
More informationPAS: A Packet Accounting System to Limit the Effects of DoS & DDoS. Debish Fesehaye & Klara Naherstedt University of Illinois-Urbana Champaign
PAS: A Packet Accountng System to Lmt the Effects of DoS & DDoS Debsh Fesehaye & Klara Naherstedt Unversty of Illnos-Urbana Champagn DoS and DDoS DDoS attacks are ncreasng threats to our dgtal world. Exstng
More informationLeast Squares Fitting of Data
Least Squares Fttng of Data Davd Eberly Geoetrc Tools, LLC http://www.geoetrctools.co/ Copyrght c 1998-2016. All Rghts Reserved. Created: July 15, 1999 Last Modfed: January 5, 2015 Contents 1 Lnear Fttng
More informationA Single-Image Super-Resolution Method for Texture Interpolation
A Sngle-Image Super-Resoluton Method for Texture Interpolaton Yaron Kalt and Moshe Porat Abstract In recent years, a number of super-resoluton technques have been proposed. Most of these technques construct
More informationDropout: A Simple Way to Prevent Neural Networks from Overfitting
Journal of Machne Learnng Research 15 (2014) 1929-1958 Submtted 11/13; Publshed 6/14 Dropout: A Smple Way to Prevent Neural Networks from Overfttng Ntsh Srvastava Geoffrey Hnton Alex Krzhevsky Ilya Sutskever
More informationUse of Numerical Models as Data Proxies for Approximate Ad-Hoc Query Processing
Preprnt UCRL-JC-?????? Use of Numercal Models as Data Proxes for Approxmate Ad-Hoc Query Processng R. Kammura, G. Abdulla, C. Baldwn, T. Crtchlow, B. Lee, I. Lozares, R. Musck, and N. Tang U.S. Department
More informationRisk-based Fatigue Estimate of Deep Water Risers -- Course Project for EM388F: Fracture Mechanics, Spring 2008
Rsk-based Fatgue Estmate of Deep Water Rsers -- Course Project for EM388F: Fracture Mechancs, Sprng 2008 Chen Sh Department of Cvl, Archtectural, and Envronmental Engneerng The Unversty of Texas at Austn
More informationCalculation of Sampling Weights
Perre Foy Statstcs Canada 4 Calculaton of Samplng Weghts 4.1 OVERVIEW The basc sample desgn used n TIMSS Populatons 1 and 2 was a two-stage stratfed cluster desgn. 1 The frst stage conssted of a sample
More informationDifferent Methods of Long-Term Electric Load Demand Forecasting; A Comprehensive Review
Dfferent Methods of Long-Term Electrc Load Demand Forecastng; A Comprehensve Revew L. Ghods* and M. Kalantar* Abstract: Long-term demand forecastng presents the frst step n plannng and developng future
More informationDescriptive Models. Cluster Analysis. Example. General Applications of Clustering. Examples of Clustering Applications
CMSC828G Prncples of Data Mnng Lecture #9 Today s Readng: HMS, chapter 9 Today s Lecture: Descrptve Modelng Clusterng Algorthms Descrptve Models model presents the man features of the data, a global summary
More informationHedging Interest-Rate Risk with Duration
FIXED-INCOME SECURITIES Chapter 5 Hedgng Interest-Rate Rsk wth Duraton Outlne Prcng and Hedgng Prcng certan cash-flows Interest rate rsk Hedgng prncples Duraton-Based Hedgng Technques Defnton of duraton
More informationOn the Use of Neural Network as a Universal Approximator
Internatonal Journal of Scences and Technques of Automatc control & computer engneerng IJ-STA, Volume, N, Jul 8, pp 386 399 On the Use of Neural Network as a Unversal Appromator Amel SIFAOUI, Afef ABDELKRIM,
More informationMechanical Properties of Evaporated Gold Films. Hard Substrate Effect Correction
Mater. Res. Soc. Symp. Proc. Vol. 1086 008 Materals Research Socety 1086-U08-41 Mechancal Propertes o vaporated Gold Flms. Hard Substrate ect Correcton Ke Du 1, Xaolu Pang 1,, Ch Chen 1, and lex. Volnsky
More informationControl Charts with Supplementary Runs Rules for Monitoring Bivariate Processes
Control Charts wth Supplementary Runs Rules for Montorng varate Processes Marcela. G. Machado *, ntono F.. Costa * * Producton Department, Sao Paulo State Unversty, Campus of Guaratnguetá, 56-4 Guaratnguetá,
More information1 Example 1: Axis-aligned rectangles
COS 511: Theoretcal Machne Learnng Lecturer: Rob Schapre Lecture # 6 Scrbe: Aaron Schld February 21, 2013 Last class, we dscussed an analogue for Occam s Razor for nfnte hypothess spaces that, n conjuncton
More informationAudio Data Mining Using Multi-perceptron Artificial Neural Network
224 IJCSNS Internatonal Journal of Computer Scence and Network Securty, VOL.8 No.0, October 2008 Audo Data Mnng Usng Mult-perceptron Artfcal Neural Network Surendra Shetty, 2 K.K. Achary Dept of Computer
More informationStatistical algorithms in Review Manager 5
Statstcal algorthms n Reve Manager 5 Jonathan J Deeks and Julan PT Hggns on behalf of the Statstcal Methods Group of The Cochrane Collaboraton August 00 Data structure Consder a meta-analyss of k studes
More informationA tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the "echo state network" approach
A tutoral on tranng recurrent neural networks, coverng BPPT, RTRL, EKF and the "echo state network" approach Herbert Jaeger Fraunhofer Insttute for Autonomous Intellgent Systems AIS) snce 2003: Internatonal
More informationLearning from Large Distributed Data: A Scaling Down Sampling Scheme for Efficient Data Processing
Internatonal Journal of Machne Learnng and Computng, Vol. 4, No. 3, June 04 Learnng from Large Dstrbuted Data: A Scalng Down Samplng Scheme for Effcent Data Processng Che Ngufor and Janusz Wojtusak part
More informationKernel Methods for General Pattern Analysis
Kernel Methods for General Pattern Analyss Nello Crstann Unversty of Calforna, Davs nello@support-vector.net Overvew Kernel Methods are a new class of pattern analyss algorthms whch can operate on very
More informationImproved SVM in Cloud Computing Information Mining
Internatonal Journal of Grd Dstrbuton Computng Vol.8, No.1 (015), pp.33-40 http://dx.do.org/10.1457/jgdc.015.8.1.04 Improved n Cloud Computng Informaton Mnng Lvshuhong (ZhengDe polytechnc college JangSu
More informationDATA MINING CLASSIFICATION ALGORITHMS FOR KIDNEY DISEASE PREDICTION
DATA MINING CLASSIFICATION ALGORITHMS FOR KIDNEY DISEASE PREDICTION Dr. S. Vjayaran 1, Mr.S.Dhayanand 2, Assstant Professor 1, M.Phl Research Scholar 2, Department of Computer Scence, School of Computer
More information