Internet Engineering. Jacek Mazurkiewicz, PhD Softcomputing. Part 3: Recurrent Artificial Neural Networks Self-Organising Artificial Neural Networks
|
|
- Amy McGee
- 5 years ago
- Views:
Transcription
1 Internet Engneerng Jacek Mazurkewcz, PhD Softcomputng Part 3: Recurrent Artfcal Neural Networks Self-Organsng Artfcal Neural Networks
2 Recurrent Artfcal Neural Networks Feedback sgnals between neurons Dynamc relatons Sngle neuron change s transmtted to whole net Stable state s reached after the set of temporary states Stable state s avalable f strct assumptons are fxed to weghts Recurrent artfcal neural networks are equped by symmetrc nter-neurons connectons
3 Assocatve Memory computer memory as close as possble to human memory: assocatve memory to store patterns learnng procedure to nprnt the set of patterns retrevng phase output the stored pattern closest to the actual nput sgnal auto-assocatve: hetero-assocatve: Smoth Smth Smth Smth s face (Smth s feature)
4 Hopfeld Network (1) w Hammng dstance for a bnary nput: x 1 v 1 y 1 d H n 1 [ x (1 y ) + (1 x ) y ] x 2 v 2 y 2 Hammng dstance equals to zero f: y x x N-1 v N-1 y N-1 Hammng dstance s a number of not equal bts x N v N y N neuron
5 Retrevng Phase (1) each neuron performs the followng two steps: computes the coproduct: p N wpv k 1 ( k+ 1) ( ) updates the state: ( + 1) v p k where: w p v (k) p p 1 for ( k+ 1) p 0 v p( k) for ( k+ 1) p 0 1 for ( k+ 1) 0 weght related to feedback sgnal feedback sgnal bas p x 1 x 2 x N-1 x N v 1 v 2 v N-1 v N w y 1 y 2 y N-1 y N neuron
6 ntal condton: Retrevng Phase (2) v ( 0) x p p p process s repeated untl convergence, whch occurs when none of the elements changes state durng any teraton: x 1 v 1 w y 1 v ( k+ 1) v ( k) y p p p p x 2 v 2 y 2 converged state of Hopfeld net means that net has already reached one of attractors attractor - pont of a local mnmum of the energy functon (Lapunov functon): x N-1 v N-1 y N-1 1 N N E( x) w x x + x E x x T T ( ) W x + x N x N v N y N neuron
7 tranng patterns are presented one by one n a ftted tme ntervals Hebban Learnng durng each nterval nput data s communcated to neuron s neghbours N tmes x 1 v 1 w y 1 w 1 N 0 M ( m) ( m) x x dla m 1 dla x 2 v 2 y 2 convergence condton: w 0 w w p pp p p p x N-1 v N-1 y N-1 algorthm: easy, fast, low memory capacty: M max N x N v N y N neuron
8 correct weght values means: nput sgnal generates tself as output converged state avalable at once: one of possble solutons s: Pseudonverse Learnng W X X x 1 x 2 v 1 v 2 w y 1 y 2 ( T ) 1 W X X X X T x N-1 v N-1 y N-1 algorthm: sophstcated, hgh memory capacty: M max N x N v N y N neuron
9 Delta-Rule Learnng weghts are tuned step by step usng all learnng sgnals, presented n a sequence: + ( ) ( ) ( ) N W W x W x x , learnng rate algorthm s qute smlar to gradent methods used for Multlayer Perceptron learnng algorthm: sophstcated, hgh memory capacty: T x 1 x 2 x N-1 v 1 v 2 v N-1 w y 1 y 2 y N-1 M max N x N v N y N neuron
10 Retrevng Phase - Problems Input sgnals heavly corrupted by nose can follow to a false answer net output s far from learned/stored patterns Energy functon value for symmetrc states s dentcal (+1,+1,-1) (-1,-1,+1) both solutons offer the same acceptance factor Learnng algorthms can produce addtonal local mnma as lnear combnaton of learnng patterns Addtonal mnma are not fxed to any learnng pattern strongly mportant f the number of learnng patterns s sgnfcant
11 Example of Answers 10 dgts, 7x7 pxels Hebban learnng: 1 correct answer Pseudonverse & Delta-rule learnng: 7 correct answers 9 answers wth 1 wrong pxel 4 answers wth 2 wrong pxels
12 Hammng Network (1)
13 Hammng Network (2) Hammng net maxmum lkelhood classfer for bnary nputs corrupted by nose Lower Sub Net calculates N mnus the Hammng dstance to M exemplar patterns Upper Sub Net selects that node wth the maxmum output All nodes use threshold logc nonlneartes the outputs of these nonlneartes never saturate Thresholds and weghts n the Maxnet are fxed All thresholds are set to zero, weghts from each node to tself are 1 Weghts between nodes are nhbtory
14 Hammng Network (3) weghts and offsets of the Lower Sub Net: w x N 2 2 weghts n the Maxnet are fxed as: for 0 N 1 and 0 M 1 wlk 1 f f k k 1 1 for 0 l, k M and 1 M all thresholds n the Maxnet are kept zero
15 Hammng Network (4) outputs of the Lower Sub Net are obtaned as: N 1 w x 0 weghts n the Maxnet are fxed as: y ( ) f ( ) t Maxnet does the maxmsaton by evaluatng: for 0 N 1 and 0 M 1 0 for 0 M 1 t t t y + f y y ( ) ( ) ( ) t k k 1 for 0, k M 1 ths process s repeated untl convergence
16 Introducton learnng wthout a teacher data overload unsupervsed learnng: smlarty PCA algorthms classfcaton archetype fndng feature maps
17 Pavlov Experment FOOD (UCS) SALIVATION (UCR) FOOD + BELL (UCS + CS) SALIVATION (CR) BELL (CS) CS condtoned stmulus UCS uncondtoned stmulus SALIVATION (CR) CR condtoned reflex UCR uncondtoned reflex
18 Felds of Usng smlarty sngle-output net how close s nput sgnal to mean-learned-pattern PCA mult-output net, each output sngle prncpal component prncpal components responsble for smlarty actual output vector correlaton level classfcaton bnary mult-output wth 1 of n code class of closest data stored patterns fndng assocatve memory codng data compresson
19 Hebban Rule (1949) f neuron A s actvated n a cyclc way by neuron B neuron A s more and more senstve to actvaton from neuron B f(a) s any functon lnear for example X 1 W 1 X 2 w ( k + 1) w( k) + w( k ) W 2 u f(a ) y w x ( k) y ( k) X m W m
20 General Hebban Rule Problem: unlmted weght growth w F( x, y ) Soluton: set lmtatons (Lnsker) Oa s rule Lmtatons: Oa s rule: Hebban rule + normalsaton addtonal requrements w w [ w, w + ] y ( k) 0; m 0 w x ( k) y ( k)[ x ( k) y ( k) w ( k)] x y w x ( k) y 0; w ( k) ( k) 0
21 Prncpal Component Analyss - PCA Statstc loss compresson n telecommuncaton Karhuenen-Loeve approach Lnear converson nto output space wth reduced dmensons preserves the most mportant features of stochastc process x Frst component estmaton weghts vector usng Oa s rule: Other prncpal components by Sanger s rule: y Wx N K R x N N K K R W R y + ) ( ) ( ) ( k x W k x W k y N T N k W x k y 0 ) ( ) (
22 Neural Networks for PCA Oa s rule Sanger s rule n k w y x y w k l 1,..., 1,..., 1 n k w y x y w l 1,..., 1,..., 1
23 Sngle-layer Rubner & Tavan Network 1989 (1) One-way connectons Weghts: nput layer calculaton layer accordng to the Hebban rule w x y Internal connectons wthn calculaton layer accordng to the ant-hebb rule v y y
24 Rubner & Tavan Network 1989 (2) y 1 y 2 y 3 y 4 v 41 v v v 21 v 32 v 43 w 11 w 45 x 1 x 2 x 3 x 4 x 5
25 Pcture Compresson for PCA Large amount of nput data substtuted by lower amount combned n vector y and W Level of compresson number of PCA components man factor of the restored pcture qualty More prncpal components better qualty lower compresson level Pcture restored based on: 2 prncpal components compresson level: 28
26 Self-Organsng Artfcal Neural Networks Inter-neurons acton Goal: nput sgnals mapped nto output sgnals Smlar nput data are grouped Groups are separated Kohonen neural network leader! T. Kohonen from Fnland!
27 Concurrent Learnng WTA Wnner Takes All WTM Wnner Takes Most W X Y
28 WTA (1) Sngle layer of workng neurons The same nput sgnals x are loaded to all compettve neurons Startng weght values are random Each neuron calculates the product: The wnner s the neuron wth a maxmum output! u w x Neuron the wnner fnal output equals to 1 Other neurons set output values to 0
29 WTA (2) Frst presentaton of learnng vectors s the base to pont the wnner neuron Weghts are modfed by the Grossberg rule If the learnng vectors are smlar the same wnner neuron, the wnner s weghts are the mean values of nput sgnals W X
30 WTM (1) Wnner selecton lke n WTA Wnner s output s maxmum Wnner actvates the neghbourhood neurons Dstance from the wnner drves the level of actvaton Level of actvaton s a part of weght tunng algorthm All weghts are modfed durng learnng algorthm
Multi-layer neural networks
Lecture 0 Mult-layer neural networks Mlos Hauskrecht mlos@cs.ptt.edu 5329 Sennott Square Lnear regresson w Lnear unts f () Logstc regresson T T = w = p( y =, w) = g( w ) w z f () = p ( y = ) w d w d Gradent
More informationCHALMERS, GÖTEBORGS UNIVERSITET. SOLUTIONS to RE-EXAM for ARTIFICIAL NEURAL NETWORKS. COURSE CODES: FFR 135, FIM 720 GU, PhD
CHALMERS, GÖTEBORGS UNIVERSITET SOLUTIONS to RE-EXAM for ARTIFICIAL NEURAL NETWORKS COURSE CODES: FFR 35, FIM 72 GU, PhD Tme: Place: Teachers: Allowed materal: Not allowed: January 2, 28, at 8 3 2 3 SB
More informationMultilayer neural networks
Lecture Multlayer neural networks Mlos Hauskrecht mlos@cs.ptt.edu 5329 Sennott Square Mdterm exam Mdterm Monday, March 2, 205 In-class (75 mnutes) closed book materal covered by February 25, 205 Multlayer
More informationMultilayer Perceptron (MLP)
Multlayer Perceptron (MLP) Seungjn Cho Department of Computer Scence and Engneerng Pohang Unversty of Scence and Technology 77 Cheongam-ro, Nam-gu, Pohang 37673, Korea seungjn@postech.ac.kr 1 / 20 Outlne
More informationHopfield networks and Boltzmann machines. Geoffrey Hinton et al. Presented by Tambet Matiisen
Hopfeld networks and Boltzmann machnes Geoffrey Hnton et al. Presented by Tambet Matsen 18.11.2014 Hopfeld network Bnary unts Symmetrcal connectons http://www.nnwj.de/hopfeld-net.html Energy functon The
More informationAdmin NEURAL NETWORKS. Perceptron learning algorithm. Our Nervous System 10/25/16. Assignment 7. Class 11/22. Schedule for the rest of the semester
0/25/6 Admn Assgnment 7 Class /22 Schedule for the rest of the semester NEURAL NETWORKS Davd Kauchak CS58 Fall 206 Perceptron learnng algorthm Our Nervous System repeat untl convergence (or for some #
More informationUnsupervised Learning
Unsupervsed Learnng Kevn Swngler What s Unsupervsed Learnng? Most smply, t can be thought of as learnng to recognse and recall thngs Recognton I ve seen that before Recall I ve seen that before and I can
More informationEEE 241: Linear Systems
EEE : Lnear Systems Summary #: Backpropagaton BACKPROPAGATION The perceptron rule as well as the Wdrow Hoff learnng were desgned to tran sngle layer networks. They suffer from the same dsadvantage: they
More informationMultilayer Perceptrons and Backpropagation. Perceptrons. Recap: Perceptrons. Informatics 1 CG: Lecture 6. Mirella Lapata
Multlayer Perceptrons and Informatcs CG: Lecture 6 Mrella Lapata School of Informatcs Unversty of Ednburgh mlap@nf.ed.ac.uk Readng: Kevn Gurney s Introducton to Neural Networks, Chapters 5 6.5 January,
More informationCHAPTER III Neural Networks as Associative Memory
CHAPTER III Neural Networs as Assocatve Memory Introducton One of the prmary functons of the bran s assocatve memory. We assocate the faces wth names, letters wth sounds, or we can recognze the people
More informationOther NN Models. Reinforcement learning (RL) Probabilistic neural networks
Other NN Models Renforcement learnng (RL) Probablstc neural networks Support vector machne (SVM) Renforcement learnng g( (RL) Basc deas: Supervsed dlearnng: (delta rule, BP) Samples (x, f(x)) to learn
More informationNeural Networks. Perceptrons and Backpropagation. Silke Bussen-Heyen. 5th of Novemeber Universität Bremen Fachbereich 3. Neural Networks 1 / 17
Neural Networks Perceptrons and Backpropagaton Slke Bussen-Heyen Unverstät Bremen Fachberech 3 5th of Novemeber 2012 Neural Networks 1 / 17 Contents 1 Introducton 2 Unts 3 Network structure 4 Snglelayer
More informationFor now, let us focus on a specific model of neurons. These are simplified from reality but can achieve remarkable results.
Neural Networks : Dervaton compled by Alvn Wan from Professor Jtendra Malk s lecture Ths type of computaton s called deep learnng and s the most popular method for many problems, such as computer vson
More informationUsing Immune Genetic Algorithm to Optimize BP Neural Network and Its Application Peng-fei LIU1,Qun-tai SHEN1 and Jun ZHI2,*
Advances n Computer Scence Research (ACRS), volume 54 Internatonal Conference on Computer Networks and Communcaton Technology (CNCT206) Usng Immune Genetc Algorthm to Optmze BP Neural Network and Its Applcaton
More informationIntroduction to the Introduction to Artificial Neural Network
Introducton to the Introducton to Artfcal Neural Netork Vuong Le th Hao Tang s sldes Part of the content of the sldes are from the Internet (possbly th modfcatons). The lecturer does not clam any onershp
More informationEvaluation of classifiers MLPs
Lecture Evaluaton of classfers MLPs Mlos Hausrecht mlos@cs.ptt.edu 539 Sennott Square Evaluaton For any data set e use to test the model e can buld a confuson matrx: Counts of examples th: class label
More information1 Convex Optimization
Convex Optmzaton We wll consder convex optmzaton problems. Namely, mnmzaton problems where the objectve s convex (we assume no constrants for now). Such problems often arse n machne learnng. For example,
More informationAssociative Memories
Assocatve Memores We consder now modes for unsupervsed earnng probems, caed auto-assocaton probems. Assocaton s the task of mappng patterns to patterns. In an assocatve memory the stmuus of an ncompete
More informationVQ widely used in coding speech, image, and video
at Scalar quantzers are specal cases of vector quantzers (VQ): they are constraned to look at one sample at a tme (memoryless) VQ does not have such constrant better RD perfomance expected Source codng
More informationLecture 23: Artificial neural networks
Lecture 23: Artfcal neural networks Broad feld that has developed over the past 20 to 30 years Confluence of statstcal mechancs, appled math, bology and computers Orgnal motvaton: mathematcal modelng of
More informationNeural network based Boolean factor analysis of parliament voting
Neural network based Boolean factor analyss of parlament votng Frolov A.A. 1, Polyakov P.Y. 2, Husek D. 3, and Rezankova H. 4 1 Insttute of Hgher Nervous Actvty and Neurophysology of the Russan Academy
More informationChapter Newton s Method
Chapter 9. Newton s Method After readng ths chapter, you should be able to:. Understand how Newton s method s dfferent from the Golden Secton Search method. Understand how Newton s method works 3. Solve
More informationLecture Notes on Linear Regression
Lecture Notes on Lnear Regresson Feng L fl@sdueducn Shandong Unversty, Chna Lnear Regresson Problem In regresson problem, we am at predct a contnuous target value gven an nput feature vector We assume
More informationMultigradient for Neural Networks for Equalizers 1
Multgradent for Neural Netorks for Equalzers 1 Chulhee ee, Jnook Go and Heeyoung Km Department of Electrcal and Electronc Engneerng Yonse Unversty 134 Shnchon-Dong, Seodaemun-Ku, Seoul 1-749, Korea ABSTRACT
More information4DVAR, according to the name, is a four-dimensional variational method.
4D-Varatonal Data Assmlaton (4D-Var) 4DVAR, accordng to the name, s a four-dmensonal varatonal method. 4D-Var s actually a drect generalzaton of 3D-Var to handle observatons that are dstrbuted n tme. The
More informationarxiv: v1 [cs.lg] 17 Jan 2019
LECTURE NOTES arxv:90.05639v [cs.lg] 7 Jan 209 Artfcal Neural Networks B. MEHLIG Department of Physcs Unversty of Gothenburg Göteborg, Sweden 209 PREFACE These are lecture notes for my course on Artfcal
More informationLECTURE NOTES. Artifical Neural Networks. B. MEHLIG (course home page)
LECTURE NOTES Artfcal Neural Networks B. MEHLIG (course home page) Department of Physcs Unversty of Gothenburg Göteborg, Sweden 208 PREFACE These are lecture notes for my course on Artfcal Neural Networks
More informationLossy Compression. Compromise accuracy of reconstruction for increased compression.
Lossy Compresson Compromse accuracy of reconstructon for ncreased compresson. The reconstructon s usually vsbly ndstngushable from the orgnal mage. Typcally, one can get up to 0:1 compresson wth almost
More informationMATH 567: Mathematical Techniques in Data Science Lab 8
1/14 MATH 567: Mathematcal Technques n Data Scence Lab 8 Domnque Gullot Departments of Mathematcal Scences Unversty of Delaware Aprl 11, 2017 Recall We have: a (2) 1 = f(w (1) 11 x 1 + W (1) 12 x 2 + W
More informationInstance-Based Learning (a.k.a. memory-based learning) Part I: Nearest Neighbor Classification
Instance-Based earnng (a.k.a. memory-based learnng) Part I: Nearest Neghbor Classfcaton Note to other teachers and users of these sldes. Andrew would be delghted f you found ths source materal useful n
More informationUnified Subspace Analysis for Face Recognition
Unfed Subspace Analyss for Face Recognton Xaogang Wang and Xaoou Tang Department of Informaton Engneerng The Chnese Unversty of Hong Kong Shatn, Hong Kong {xgwang, xtang}@e.cuhk.edu.hk Abstract PCA, LDA
More informationHopfield Training Rules 1 N
Hopfeld Tranng Rules To memorse a sngle pattern Suppose e set the eghts thus - = p p here, s the eght beteen nodes & s the number of nodes n the netor p s the value requred for the -th node What ll the
More information1 Input-Output Mappings. 2 Hebbian Failure. 3 Delta Rule Success.
Task Learnng 1 / 27 1 Input-Output Mappngs. 2 Hebban Falure. 3 Delta Rule Success. Input-Output Mappngs 2 / 27 0 1 2 3 4 5 6 7 8 9 Output 3 8 2 7 Input 5 6 0 9 1 4 Make approprate: Response gven stmulus.
More informationNon-linear Canonical Correlation Analysis Using a RBF Network
ESANN' proceedngs - European Smposum on Artfcal Neural Networks Bruges (Belgum), 4-6 Aprl, d-sde publ., ISBN -97--, pp. 57-5 Non-lnear Canoncal Correlaton Analss Usng a RBF Network Sukhbnder Kumar, Elane
More informationLecture 10 Support Vector Machines II
Lecture 10 Support Vector Machnes II 22 February 2016 Taylor B. Arnold Yale Statstcs STAT 365/665 1/28 Notes: Problem 3 s posted and due ths upcomng Frday There was an early bug n the fake-test data; fxed
More informationKernels in Support Vector Machines. Based on lectures of Martin Law, University of Michigan
Kernels n Support Vector Machnes Based on lectures of Martn Law, Unversty of Mchgan Non Lnear separable problems AND OR NOT() The XOR problem cannot be solved wth a perceptron. XOR Per Lug Martell - Systems
More informationHOPFIELD NETWORKS 9.1 INTRODUCTION
UNI 9 HOPFIELD NEWORKS Structure Page No. 9. Introducton 9 Objectves 9. Related Defntons 0 9. Hopfeld Networs 9.4 Structure of Hopfeld Networs 5 9.5 he Functonalty of Hopfeld Networs 6 9.6 Storage Capacty
More informationDiscriminative classifier: Logistic Regression. CS534-Machine Learning
Dscrmnatve classfer: Logstc Regresson CS534-Machne Learnng 2 Logstc Regresson Gven tranng set D stc regresson learns the condtonal dstrbuton We ll assume onl to classes and a parametrc form for here s
More informationImage Segmentation and Compression using Neural Networks
Image Segmentaton and Compresson usng Neural Networks Constantno Carlos Reyes-Aldasoro, Ana Laura Aldeco Departamento de Sstemas Dgtales Insttuto Tecnológco Autónomo de Méxco Río Hondo No. 1, Tzapán San
More informationThe Cortex. Networks. Laminar Structure of Cortex. Chapter 3, O Reilly & Munakata.
Networks The Cortex Chapter, O Relly & Munakata. Bology of networks: The cortex Exctaton: Undrectonal (transformatons) Local vs. dstrbuted representatons Bdrectonal (pattern completon, amplfcaton) Inhbton:
More informationModule 3 LOSSY IMAGE COMPRESSION SYSTEMS. Version 2 ECE IIT, Kharagpur
Module 3 LOSSY IMAGE COMPRESSION SYSTEMS Verson ECE IIT, Kharagpur Lesson 6 Theory of Quantzaton Verson ECE IIT, Kharagpur Instructonal Objectves At the end of ths lesson, the students should be able to:
More informationLinear Feature Engineering 11
Lnear Feature Engneerng 11 2 Least-Squares 2.1 Smple least-squares Consder the followng dataset. We have a bunch of nputs x and correspondng outputs y. The partcular values n ths dataset are x y 0.23 0.19
More informationSupport Vector Machines
Support Vector Machnes Konstantn Tretyakov (kt@ut.ee) MTAT.03.227 Machne Learnng So far Supervsed machne learnng Lnear models Least squares regresson Fsher s dscrmnant, Perceptron, Logstc model Non-lnear
More informationNeural networks. Nuno Vasconcelos ECE Department, UCSD
Neural networs Nuno Vasconcelos ECE Department, UCSD Classfcaton a classfcaton problem has two types of varables e.g. X - vector of observatons (features) n the world Y - state (class) of the world x X
More informationNonlinear Classifiers II
Nonlnear Classfers II Nonlnear Classfers: Introducton Classfers Supervsed Classfers Lnear Classfers Perceptron Least Squares Methods Lnear Support Vector Machne Nonlnear Classfers Part I: Mult Layer Neural
More informationCourse 395: Machine Learning - Lectures
Course 395: Machne Learnng - Lectures Lecture 1-2: Concept Learnng (M. Pantc Lecture 3-4: Decson Trees & CC Intro (M. Pantc Lecture 5-6: Artfcal Neural Networks (S.Zaferou Lecture 7-8: Instance ased Learnng
More informationSupport Vector Machines
Support Vector Machnes Konstantn Tretyakov (kt@ut.ee) MTAT.03.227 Machne Learnng So far So far Supervsed machne learnng Lnear models Non-lnear models Unsupervsed machne learnng Generc scaffoldng So far
More informationMicrowave Diversity Imaging Compression Using Bioinspired
Mcrowave Dversty Imagng Compresson Usng Bonspred Neural Networks Youwe Yuan 1, Yong L 1, Wele Xu 1, Janghong Yu * 1 School of Computer Scence and Technology, Hangzhou Danz Unversty, Hangzhou, Zhejang,
More informationClassification as a Regression Problem
Target varable y C C, C,, ; Classfcaton as a Regresson Problem { }, 3 L C K To treat classfcaton as a regresson problem we should transform the target y nto numercal values; The choce of numercal class
More informationOutline. Communication. Bellman Ford Algorithm. Bellman Ford Example. Bellman Ford Shortest Path [1]
DYNAMIC SHORTEST PATH SEARCH AND SYNCHRONIZED TASK SWITCHING Jay Wagenpfel, Adran Trachte 2 Outlne Shortest Communcaton Path Searchng Bellmann Ford algorthm Algorthm for dynamc case Modfcatons to our algorthm
More informationLecture 10 Support Vector Machines. Oct
Lecture 10 Support Vector Machnes Oct - 20-2008 Lnear Separators Whch of the lnear separators s optmal? Concept of Margn Recall that n Perceptron, we learned that the convergence rate of the Perceptron
More informationUncertainty in measurements of power and energy on power networks
Uncertanty n measurements of power and energy on power networks E. Manov, N. Kolev Department of Measurement and Instrumentaton, Techncal Unversty Sofa, bul. Klment Ohrdsk No8, bl., 000 Sofa, Bulgara Tel./fax:
More informationCSci 6974 and ECSE 6966 Math. Tech. for Vision, Graphics and Robotics Lecture 21, April 17, 2006 Estimating A Plane Homography
CSc 6974 and ECSE 6966 Math. Tech. for Vson, Graphcs and Robotcs Lecture 21, Aprl 17, 2006 Estmatng A Plane Homography Overvew We contnue wth a dscusson of the major ssues, usng estmaton of plane projectve
More informationThe Hopfield model. 1 The Hebbian paradigm. Sebastian Seung Lecture 15: November 7, 2002
MIT Department of Bran and Cogntve Scences 9.29J, Sprng 2004 - Introducton to Computatonal euroscence Instructor: Professor Sebastan Seung The Hopfeld model Sebastan Seung 9.64 Lecture 5: ovember 7, 2002
More informationCHAPTER 5 NUMERICAL EVALUATION OF DYNAMIC RESPONSE
CHAPTER 5 NUMERICAL EVALUATION OF DYNAMIC RESPONSE Analytcal soluton s usually not possble when exctaton vares arbtrarly wth tme or f the system s nonlnear. Such problems can be solved by numercal tmesteppng
More informationDesign and Optimization of Fuzzy Controller for Inverse Pendulum System Using Genetic Algorithm
Desgn and Optmzaton of Fuzzy Controller for Inverse Pendulum System Usng Genetc Algorthm H. Mehraban A. Ashoor Unversty of Tehran Unversty of Tehran h.mehraban@ece.ut.ac.r a.ashoor@ece.ut.ac.r Abstract:
More information1 Derivation of Rate Equations from Single-Cell Conductance (Hodgkin-Huxley-like) Equations
Physcs 171/271 -Davd Klenfeld - Fall 2005 (revsed Wnter 2011) 1 Dervaton of Rate Equatons from Sngle-Cell Conductance (Hodgkn-Huxley-lke) Equatons We consder a network of many neurons, each of whch obeys
More informationCSE 252C: Computer Vision III
CSE 252C: Computer Vson III Lecturer: Serge Belonge Scrbe: Catherne Wah LECTURE 15 Kernel Machnes 15.1. Kernels We wll study two methods based on a specal knd of functon k(x, y) called a kernel: Kernel
More informationp 1 c 2 + p 2 c 2 + p 3 c p m c 2
Where to put a faclty? Gven locatons p 1,..., p m n R n of m houses, want to choose a locaton c n R n for the fre staton. Want c to be as close as possble to all the house. We know how to measure dstance
More informationGradient Descent Learning and Backpropagation
Artfcal Neural Networks (art 2) Chrstan Jacob Gradent Descent Learnng and Backpropagaton CSC 533 Wnter 200 Learnng by Gradent Descent Defnton of the Learnng roble Let us start wth the sple case of lnear
More informationEnergy Storage Elements: Capacitors and Inductors
CHAPTER 6 Energy Storage Elements: Capactors and Inductors To ths pont n our study of electronc crcuts, tme has not been mportant. The analyss and desgns we hae performed so far hae been statc, and all
More informationPrincipe, J.C. Artificial Neural Networks The Electrical Engineering Handbook Ed. Richard C. Dorf Boca Raton: CRC Press LLC, 2000
Prncpe, J.C. Artfcal Neural Networks The Electrcal Engneerng Handbook Ed. Rchard C. Dorf Boca Raton: CRC Press LLC, 2000 20 Artfcal Neural Networks Jose C. Prncpe Unversty of Florda 20.1 Defntons and Scope
More information10-701/ Machine Learning, Fall 2005 Homework 3
10-701/15-781 Machne Learnng, Fall 2005 Homework 3 Out: 10/20/05 Due: begnnng of the class 11/01/05 Instructons Contact questons-10701@autonlaborg for queston Problem 1 Regresson and Cross-valdaton [40
More informationRadial-Basis Function Networks
Radal-Bass uncton Networs v.0 March 00 Mchel Verleysen Radal-Bass uncton Networs - Radal-Bass uncton Networs p Orgn: Cover s theorem p Interpolaton problem p Regularzaton theory p Generalzed RBN p Unversal
More informationDetermining Transmission Losses Penalty Factor Using Adaptive Neuro Fuzzy Inference System (ANFIS) For Economic Dispatch Application
7 Determnng Transmsson Losses Penalty Factor Usng Adaptve Neuro Fuzzy Inference System (ANFIS) For Economc Dspatch Applcaton Rony Seto Wbowo Maurdh Hery Purnomo Dod Prastanto Electrcal Engneerng Department,
More informationProblem Set 9 Solutions
Desgn and Analyss of Algorthms May 4, 2015 Massachusetts Insttute of Technology 6.046J/18.410J Profs. Erk Demane, Srn Devadas, and Nancy Lynch Problem Set 9 Solutons Problem Set 9 Solutons Ths problem
More informationGenerative classification models
CS 675 Intro to Machne Learnng Lecture Generatve classfcaton models Mlos Hauskrecht mlos@cs.ptt.edu 539 Sennott Square Data: D { d, d,.., dn} d, Classfcaton represents a dscrete class value Goal: learn
More informationPulse Coded Modulation
Pulse Coded Modulaton PCM (Pulse Coded Modulaton) s a voce codng technque defned by the ITU-T G.711 standard and t s used n dgtal telephony to encode the voce sgnal. The frst step n the analog to dgtal
More informationLogistic Regression. CAP 5610: Machine Learning Instructor: Guo-Jun QI
Logstc Regresson CAP 561: achne Learnng Instructor: Guo-Jun QI Bayes Classfer: A Generatve model odel the posteror dstrbuton P(Y X) Estmate class-condtonal dstrbuton P(X Y) for each Y Estmate pror dstrbuton
More informationAutomatic Object Trajectory- Based Motion Recognition Using Gaussian Mixture Models
Automatc Object Trajectory- Based Moton Recognton Usng Gaussan Mxture Models Fasal I. Bashr, Ashfaq A. Khokhar, Dan Schonfeld Electrcal and Computer Engneerng, Unversty of Illnos at Chcago. Chcago, IL,
More informationNeural Networks. Neural Network Motivation. Why Neural Networks? Comments on Blue Gene. More Comments on Blue Gene
Motvaton for non-lnear Classfers Neural Networs CPS 27 Ron Parr Lnear methods are wea Mae strong assumptons Can only express relatvely smple functons of nputs Comng up wth good features can be hard Why
More information9 Derivation of Rate Equations from Single-Cell Conductance (Hodgkin-Huxley-like) Equations
Physcs 171/271 - Chapter 9R -Davd Klenfeld - Fall 2005 9 Dervaton of Rate Equatons from Sngle-Cell Conductance (Hodgkn-Huxley-lke) Equatons We consder a network of many neurons, each of whch obeys a set
More informationNegative Binomial Regression
STATGRAPHICS Rev. 9/16/2013 Negatve Bnomal Regresson Summary... 1 Data Input... 3 Statstcal Model... 3 Analyss Summary... 4 Analyss Optons... 7 Plot of Ftted Model... 8 Observed Versus Predcted... 10 Predctons...
More informationNeural Networks & Learning
Neural Netorks & Learnng. Introducton The basc prelmnares nvolved n the Artfcal Neural Netorks (ANN) are descrbed n secton. An Artfcal Neural Netorks (ANN) s an nformaton-processng paradgm that nspred
More informationRemoval of Hidden Neurons by Crosswise Propagation
Neural Informaton Processng - etters and Revews Vol.6 No.3 arch 25 ETTER Removal of dden Neurons by Crosswse Propagaton Xun ang Department of anagement Scence and Engneerng Stanford Unversty CA 9535 USA
More informationMDL-Based Unsupervised Attribute Ranking
MDL-Based Unsupervsed Attrbute Rankng Zdravko Markov Computer Scence Department Central Connectcut State Unversty New Brtan, CT 06050, USA http://www.cs.ccsu.edu/~markov/ markovz@ccsu.edu MDL-Based Unsupervsed
More informationThe Gaussian classifier. Nuno Vasconcelos ECE Department, UCSD
he Gaussan classfer Nuno Vasconcelos ECE Department, UCSD Bayesan decson theory recall that we have state of the world X observatons g decson functon L[g,y] loss of predctng y wth g Bayes decson rule s
More informationCIS526: Machine Learning Lecture 3 (Sept 16, 2003) Linear Regression. Preparation help: Xiaoying Huang. x 1 θ 1 output... θ M x M
CIS56: achne Learnng Lecture 3 (Sept 6, 003) Preparaton help: Xaoyng Huang Lnear Regresson Lnear regresson can be represented by a functonal form: f(; θ) = θ 0 0 +θ + + θ = θ = 0 ote: 0 s a dummy attrbute
More informationLecture 3: Shannon s Theorem
CSE 533: Error-Correctng Codes (Autumn 006 Lecture 3: Shannon s Theorem October 9, 006 Lecturer: Venkatesan Guruswam Scrbe: Wdad Machmouch 1 Communcaton Model The communcaton model we are usng conssts
More informationTracking with Kalman Filter
Trackng wth Kalman Flter Scott T. Acton Vrgna Image and Vdeo Analyss (VIVA), Charles L. Brown Department of Electrcal and Computer Engneerng Department of Bomedcal Engneerng Unversty of Vrgna, Charlottesvlle,
More informationBoise State University Department of Electrical and Computer Engineering ECE 212L Circuit Analysis and Design Lab
Bose State Unersty Department of Electrcal and omputer Engneerng EE 1L rcut Analyss and Desgn Lab Experment #8: The Integratng and Dfferentatng Op-Amp rcuts 1 Objectes The objectes of ths laboratory experment
More informationIntroduction to Vapor/Liquid Equilibrium, part 2. Raoult s Law:
CE304, Sprng 2004 Lecture 4 Introducton to Vapor/Lqud Equlbrum, part 2 Raoult s Law: The smplest model that allows us do VLE calculatons s obtaned when we assume that the vapor phase s an deal gas, and
More informationCurve Fitting with the Least Square Method
WIKI Document Number 5 Interpolaton wth Least Squares Curve Fttng wth the Least Square Method Mattheu Bultelle Department of Bo-Engneerng Imperal College, London Context We wsh to model the postve feedback
More informationRBF Neural Network Model Training by Unscented Kalman Filter and Its Application in Mechanical Fault Diagnosis
Appled Mechancs and Materals Submtted: 24-6-2 ISSN: 662-7482, Vols. 62-65, pp 2383-2386 Accepted: 24-6- do:.428/www.scentfc.net/amm.62-65.2383 Onlne: 24-8- 24 rans ech Publcatons, Swtzerland RBF Neural
More informationCSC321 Tutorial 9: Review of Boltzmann machines and simulated annealing
CSC321 Tutoral 9: Revew of Boltzmann machnes and smulated annealng (Sldes based on Lecture 16-18 and selected readngs) Yue L Emal: yuel@cs.toronto.edu Wed 11-12 March 19 Fr 10-11 March 21 Outlne Boltzmann
More informationMULTISPECTRAL IMAGE CLASSIFICATION USING BACK-PROPAGATION NEURAL NETWORK IN PCA DOMAIN
MULTISPECTRAL IMAGE CLASSIFICATION USING BACK-PROPAGATION NEURAL NETWORK IN PCA DOMAIN S. Chtwong, S. Wtthayapradt, S. Intajag, and F. Cheevasuvt Faculty of Engneerng, Kng Mongkut s Insttute of Technology
More informationSupport Vector Machines. Vibhav Gogate The University of Texas at dallas
Support Vector Machnes Vbhav Gogate he Unversty of exas at dallas What We have Learned So Far? 1. Decson rees. Naïve Bayes 3. Lnear Regresson 4. Logstc Regresson 5. Perceptron 6. Neural networks 7. K-Nearest
More informationModel of Neurons. CS 416 Artificial Intelligence. Early History of Neural Nets. Cybernetics. McCulloch-Pitts Neurons. Hebbian Modification.
Page 1 Model of Neurons CS 416 Artfcal Intellgence Lecture 18 Neural Nets Chapter 20 Multple nputs/dendrtes (~10,000!!!) Cell body/soma performs computaton Sngle output/axon Computaton s typcally modeled
More informationMLE and Bayesian Estimation. Jie Tang Department of Computer Science & Technology Tsinghua University 2012
MLE and Bayesan Estmaton Je Tang Department of Computer Scence & Technology Tsnghua Unversty 01 1 Lnear Regresson? As the frst step, we need to decde how we re gong to represent the functon f. One example:
More informationCalculation of time complexity (3%)
Problem 1. (30%) Calculaton of tme complexty (3%) Gven n ctes, usng exhaust search to see every result takes O(n!). Calculaton of tme needed to solve the problem (2%) 40 ctes:40! dfferent tours 40 add
More informationEnsemble Methods: Boosting
Ensemble Methods: Boostng Ncholas Ruozz Unversty of Texas at Dallas Based on the sldes of Vbhav Gogate and Rob Schapre Last Tme Varance reducton va baggng Generate new tranng data sets by samplng wth replacement
More informationSolving Nonlinear Differential Equations by a Neural Network Method
Solvng Nonlnear Dfferental Equatons by a Neural Network Method Luce P. Aarts and Peter Van der Veer Delft Unversty of Technology, Faculty of Cvlengneerng and Geoscences, Secton of Cvlengneerng Informatcs,
More informationSuppose that there s a measured wndow of data fff k () ; :::; ff k g of a sze w, measured dscretely wth varable dscretzaton step. It s convenent to pl
RECURSIVE SPLINE INTERPOLATION METHOD FOR REAL TIME ENGINE CONTROL APPLICATIONS A. Stotsky Volvo Car Corporaton Engne Desgn and Development Dept. 97542, HA1N, SE- 405 31 Gothenburg Sweden. Emal: astotsky@volvocars.com
More information8 Derivation of Network Rate Equations from Single- Cell Conductance Equations
Physcs 178/278 - Davd Klenfeld - Wnter 2015 8 Dervaton of Network Rate Equatons from Sngle- Cell Conductance Equatons We consder a network of many neurons, each of whch obeys a set of conductancebased,
More informationAn Interactive Optimisation Tool for Allocation Problems
An Interactve Optmsaton ool for Allocaton Problems Fredr Bonäs, Joam Westerlund and apo Westerlund Process Desgn Laboratory, Faculty of echnology, Åbo Aadem Unversty, uru 20500, Fnland hs paper presents
More informationAstronomical Object Recognition by means of Neural Networks.
Astronomcal Obect Recognton by means of Neural Networks. R. Taglaferr DMI - Unverstà d Salerno, 84081 Baronss (Salerno) and I.N.F.M. Untà d Salerno, 84081 Baronss (Salerno) and IIASS E. R. Caanello, 84019
More informationSupport Vector Machines
CS 2750: Machne Learnng Support Vector Machnes Prof. Adrana Kovashka Unversty of Pttsburgh February 17, 2016 Announcement Homework 2 deadlne s now 2/29 We ll have covered everythng you need today or at
More informationDiscriminative classifier: Logistic Regression. CS534-Machine Learning
Dscrmnatve classfer: Logstc Regresson CS534-Machne Learnng robablstc Classfer Gven an nstance, hat does a probablstc classfer do dfferentl compared to, sa, perceptron? It does not drectl predct Instead,
More informationMarkov Chain Monte Carlo Lecture 6
where (x 1,..., x N ) X N, N s called the populaton sze, f(x) f (x) for at least one {1, 2,..., N}, and those dfferent from f(x) are called the tral dstrbutons n terms of mportance samplng. Dfferent ways
More informationRegularized Discriminant Analysis for Face Recognition
1 Regularzed Dscrmnant Analyss for Face Recognton Itz Pma, Mayer Aladem Department of Electrcal and Computer Engneerng, Ben-Guron Unversty of the Negev P.O.Box 653, Beer-Sheva, 845, Israel. Abstract Ths
More information