The Backpropagation Algorithm

Size: px
Start display at page:

Download "The Backpropagation Algorithm"

Transcription

1 The Backpopagaton Algothm Achtectue of Feedfowad Netwok Sgmodal Thehold Functon Contuctng an Obectve Functon Tanng a one-laye netwok by teepet decent Tanng a two-laye netwok by teepet decent Copyght Robet R. Snapp 202 CS 295 (UVM) The Backpopagaton Algothm Fall 203 / 20

2 Feedfowad Netwok: Nomenclatue Conde a feedfowad netwok f W R n! R N, one wth n eal nput and N output unt. Aume thee ae L laye of lnea thehold unt, wth n unt n laye n 2 unt n laye 2 : n L N unt n laye L Let n 0 n, and let y.`/ denote the output value of unt n laye `, denote the ynaptc weght of unt n laye ` that appled to the output of unt fom laye `, w.`/ ; w.`/ ;0 denote the ntenal ba of unt n laye `. Note, fo ; 2; : : : ; n`, y.`/ gn n` X w.`/.` / ; y C w.`/ ;0 ; wth, y.0/ x : CS 295 (UVM) The Backpopagaton Algothm Fall / 20

3 Feedfowad netwok (cont.) (0) y =x w (),2 y () w,0 () w (2) 2, y (2) w,0 (2) y (l) w,0 (l) w (L),0 y (L) (0) y 2 =x 2 y () w 2,0 () 2 y (2) w 2,0 (2) 2 y (l) w 2,0 (l) 2 w (L) 2,0 y (L) 2 (0) y 3 =x 3 y () w 3,0 () 3 y (2) w 3,0 (2) 3 y (l) w 3,0 (l) 3 w (L) 3,0 y (L) 3 (0) y n0 =x n0 w () n,0 w (2) n 2,0 y () n y (2) n 2 w (l) n l,0 y (l) n l w (L) n L,0 y (L) n L Numbe of bae and weght =. C n 0 /n C. C n /n 2 C : : : C. C n L /n L. Fo ` ; 2; : : : ; n L, y.`/ gn n` X w.`/.` / ; y C w.`/ ;0 ; fo ; 2; : : : ; n`. : CS 295 (UVM) The Backpopagaton Algothm Fall / 20

4 Supeved Leanng Paadgm Let, denote a tanng et of m patten, wth X m.x./ ; t./ /; : : : ;.x.m/ ; t.m/ /g x.p/ 2 R n 0 and 2 R n L ; fo p ; 2; : : : ; m. n o n o Goal: Fnd bae and weght W ; : : : ; o that the netwok w./ ; output unt decbe a vecto n R n L that le uffcently cloe to the taget vecto, wheneve the nput unt coepond to the nput vecto x.p/, fo p ; 2; : : : ; m. Method: Fnd the weght that mnmze the LMS obectve functon E.W/ w.l/ ; mx E p.w/; whee, p E p.w/ def 2 y.l/ x.p/ 2 ; W 2 n L X 2 y.l/ x.p/ ; W : CS 295 (UVM) The Backpopagaton Algothm Fall / 20

5 Weght pace fo the Neual Netwok The numbe of bae and weght n the neual netwok gven by W. C n 0 /n C. C n /n 2 C C. C n L /n L : The tate of the netwok at epoch t can thu be epeented a a pont w.t/ 2 R n the -dmenonal weght @ def ; ; : : denote the -dmenonal gadent. The netwok can be taned by gadent decent: Intalze the netwok wth weght w.0/. 2 Select two potve paamete, ; > 0. 3 Whle E.t/ >, update the weght by the ule, T w.t C / w.t/ E w.t/ : CS 295 (UVM) The Backpopagaton Algothm Fall / 20

6 ffeent Mode of Leanng The pevouly defned leanng ule w.t C / w.t/ E w.t/ ; wth E.w/ mx E p.w/; whee, p E p.w/ def 2 y.l/ x.p/ 2 ; w 2 n L X 2 y.l/ x.p/ ; w ; called a batch update ule. The equental update ule defned, altenatvely, by w.t C / w.t/ E p.t/ w.t/ ; whee p.t/ denote the patten ndex that elected at epoch t. Fo example, p.t/ t mod m C, fo a equental cyclc update ule, o p.t/ andœ; m, fo a equental andom update ule. CS 295 (UVM) The Backpopagaton Algothm Fall / 20

7 Sgmodal Functon The applcaton of ethe ule eque that the gadent of E p be defned. We thu need to eplace the dcontnuou gnum (o gn) functon gn n each LTU wth a mooth appoxmaton, whch we call a gmodal functon. We uually eque that be monotonc, wth 0.u/ > 0; fo < u < C, and lm.u/ ; lm.u/ C; and,.0/ 0: u! u!c.u/ u CS 295 (UVM) The Backpopagaton Algothm Fall / 20

8 Sgmodal Functon (cont.) Fo example, we let whence, e u.u/ eu tanh u; e u C e u 0.u/ d du.eu C e u /.e u e u / 0.e u e u /.e u C e u / 0.e u C e u / 2 4.e u C e u / 2 ech2 u tanh 2 u 2.u/: CS 295 (UVM) The Backpopagaton Algothm Fall / 20

9 Sgmodal Functon (cont.) Altenatvely, f one dee the output ange to be wthn the unt nteval, let, fo whch,.u/ e u e u C e u C e 2u ; lm.u/ 0;.0/ u! 2 ; lm.u/ u!c 0.u/ 2 e 2u C e 2u 2 2.u/.u/ :.u/ O u CS 295 (UVM) The Backpopagaton Algothm Fall / 20

10 Sgmodal Fucnton (cont.) Anothe ueful choce.u/ 2 tan u; wth, 0.u/ 2 a th 0.u/ (uually) eman nonzeo n dgtal mulaton. C u 2 ; When t deable to model a geneal analytc functon, W R n 0! R n L t often ueful to employ lnea thehold functon n the output laye:.u/ u; 0.u/ : CS 295 (UVM) The Backpopagaton Algothm Fall / 20

11 Notatonal Conventon It advantageou to defne y.0/ y.`/ ( f 0 x f n 0 8 < f 0 : Pn` w.`/.` / f n` 0 ; y fo l ; 2; : : : ; L. Notaton alo mplfed by defnng S.`/ X n` def w.`/.` / ; y 0 CS 295 (UVM) The Backpopagaton Algothm Fall 203 / 20

12 One-Laye Netwok Ft, conde the cae L, o that the netwok cont of n 0 nput unt, and n output unt. p 2 Xn Xn y./ x.p/ I w 2 y./ x.p/ I y./ x.p/ I : y./ x.p/ I w CS 295 (UVM) The Backpopagaton Algothm Fall / 20

13 One-Laye S./ 0 X n S./ / ; y.0/ 0 X n S./ 0 ı ; ı ; y.0/ 0 S./ ı ; y.0/ whee, ı ;ˇ ( f ˇ 0 f ˇ, denote the Konecke delta functon. CS 295 (UVM) The Backpopagaton Algothm Fall / 20

14 One-Laye Netwok (cont.) Subttuton nto the pevou equaton p Xn y./ x.p/ I w 0 S./ ı ; y.0/ y./ x.p/ I w 0 S./ y.0/ ;./ y.0/ whee./ def y./ x.p/ I w 0 S./ : Thu, fo ; 2; : : : ; n and 0; ; 2; : : : ; n 0, w././.t C / w.t/ C./ y.0/ CS 295 (UVM) The Backpopagaton Algothm Fall / 20

15 Two-Laye Netwok: econd-laye weght Now, let L 2. Thu the netwok ha n 0 nput unt, one laye of n hdden unt, and one laye of n 2 output unt. The numbe of bae and weght.n 0 C /n C.n C /n 2. By the pecedng analy, t can be hown that fo ; : : : ; n 2, and 0; ; 2; : : : ; p y./ ; def y.2/ x.p/ I w 0 S.2/ : CS 295 (UVM) The Backpopagaton Algothm Fall / 20

16 Two-Laye Netwok: ft-laye p 2 Xn Xn 2 Xn 2 y.2/ x.p/ I w 2 y.2/ x.p/ I y.2/ x.p/ I y.2/ x.p/ I w We S.2/ 0 X n S.2/ 0.2/ w.2/ 0 X n S.2/ : (Why?) 0 w.2/ ; CS 295 (UVM) The Backpopagaton Algothm Fall / 20

17 Two-Laye Netwok: ft-laye weght (cont.) Fom the analy of the one-laye 0 S./ ı ; y.0/ : Thu, by 0 X n S.2/ w.2/ 0 X n S.2/ w.2/ ; 0 S./ ı ; y.0/ ; 0 S.2/ w.2/ ; 0 S./ ; y.0/ : CS 295 (UVM) The Backpopagaton Algothm Fall / 20

18 Two-Laye Netwok: ft-laye weght (cont.) Recall that Thu, p def Xn 2 Xn 2 Xn 2 S./ Pn2 0 S.2/ w.2/ ; 0 S./ y.0/ ; and y.2/ x.p/ I w 0 S.2/ y.2/ x.p/ I y.2/ x.p/ I w 0 S.2/.2/ w.2/ ; 0 S./ y.0/./ y.0/ ;.2/ w.2/ ;. w.2/ ; 0 S./ y.0/ CS 295 (UVM) The Backpopagaton Algothm Fall / 20

19 L-laye feedfowad netwok The equental update ule eadly genealzed to L laye: At epoch t peent patten p p.t/, x.p/ to the nput unt: ( y.0/ f 0 x.p/ f n 0 2 Fo ` ; 2; : : : ; L, compute y.`/ whee S.`/ P n` 0 w.`/.` / ; y ( ; f 0 ; f n`; S.`/ 3 Compute the eo of each output unt,.l/ y.l/ fo ; 2; : : : ; n L.. (The gnal popagate fowad.) x.p/ I w 0 S.L/ ; CS 295 (UVM) The Backpopagaton Algothm Fall / 20

20 L-laye feedfowad netwok (cont.) 4 Popagate the eo backwad though the netwok by computng fo ` L ; L 2; : : : ;,.`/ 0 S.`/ n`c X fo ; 2; : : : ; n`. (Eo popagate backwad.) 5 Update the weght: w.`/ ;.`C/ w.`c/ ; ;.t C / w.`/.t/ C.`/ ;.` / y ; fo ` ; 2; : : : ; L; ; 2; : : : n`; and 0; ; : : : ; n`. CS 295 (UVM) The Backpopagaton Algothm Fall / 20

EE 5337 Computational Electromagnetics (CEM)

EE 5337 Computational Electromagnetics (CEM) 7//28 Instucto D. Raymond Rumpf (95) 747 6958 cumpf@utep.edu EE 5337 Computatonal Electomagnetcs (CEM) Lectue #6 TMM Extas Lectue 6These notes may contan copyghted mateal obtaned unde fa use ules. Dstbuton

More information

Learning the structure of Bayesian belief networks

Learning the structure of Bayesian belief networks Lectue 17 Leanng the stuctue of Bayesan belef netwoks Mlos Hauskecht mlos@cs.ptt.edu 5329 Sennott Squae Leanng of BBN Leanng. Leanng of paametes of condtonal pobabltes Leanng of the netwok stuctue Vaables:

More information

8 Baire Category Theorem and Uniform Boundedness

8 Baire Category Theorem and Uniform Boundedness 8 Bae Categoy Theoem and Unfom Boundedness Pncple 8.1 Bae s Categoy Theoem Valdty of many esults n analyss depends on the completeness popety. Ths popety addesses the nadequacy of the system of atonal

More information

Detection and Estimation Theory

Detection and Estimation Theory ESE 54 Detecton and Etmaton Theoy Joeph A. O Sullvan Samuel C. Sach Pofeo Electonc Sytem and Sgnal Reeach Laboatoy Electcal and Sytem Engneeng Wahngton Unvety 411 Jolley Hall 314-935-4173 (Lnda anwe) jao@wutl.edu

More information

Set of square-integrable function 2 L : function space F

Set of square-integrable function 2 L : function space F Set of squae-ntegable functon L : functon space F Motvaton: In ou pevous dscussons we have seen that fo fee patcles wave equatons (Helmholt o Schödnge) can be expessed n tems of egenvalue equatons. H E,

More information

Multilayer Perceptron (MLP)

Multilayer 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 information

Exam 1. Sept. 22, 8:00-9:30 PM EE 129. Material: Chapters 1-8 Labs 1-3

Exam 1. Sept. 22, 8:00-9:30 PM EE 129. Material: Chapters 1-8 Labs 1-3 Eam ept., 8:00-9:30 PM EE 9 Mateal: Chapte -8 Lab -3 tandadzaton and Calbaton: Ttaton: ue of tandadzed oluton to detemne the concentaton of an unknown. Rele on a eacton of known tochomet, a oluton wth

More information

If there are k binding constraints at x then re-label these constraints so that they are the first k constraints.

If there are k binding constraints at x then re-label these constraints so that they are the first k constraints. Mathematcal Foundatons -1- Constaned Optmzaton Constaned Optmzaton Ma{ f ( ) X} whee X {, h ( ), 1,, m} Necessay condtons fo to be a soluton to ths mamzaton poblem Mathematcally, f ag Ma{ f ( ) X}, then

More information

Multistage Median Ranked Set Sampling for Estimating the Population Median

Multistage Median Ranked Set Sampling for Estimating the Population Median Jounal of Mathematcs and Statstcs 3 (: 58-64 007 ISSN 549-3644 007 Scence Publcatons Multstage Medan Ranked Set Samplng fo Estmatng the Populaton Medan Abdul Azz Jeman Ame Al-Oma and Kamaulzaman Ibahm

More information

Thermodynamics of solids 4. Statistical thermodynamics and the 3 rd law. Kwangheon Park Kyung Hee University Department of Nuclear Engineering

Thermodynamics of solids 4. Statistical thermodynamics and the 3 rd law. Kwangheon Park Kyung Hee University Department of Nuclear Engineering Themodynamcs of solds 4. Statstcal themodynamcs and the 3 d law Kwangheon Pak Kyung Hee Unvesty Depatment of Nuclea Engneeng 4.1. Intoducton to statstcal themodynamcs Classcal themodynamcs Statstcal themodynamcs

More information

Solving the Dirac Equation: Using Fourier Transform

Solving the Dirac Equation: Using Fourier Transform McNa Schola Reeach Jounal Volume Atcle Solvng the ac quaton: Ung oue Tanfom Vncent P. Bell mby-rddle Aeonautcal Unvety, Vncent.Bell@my.eau.edu ollow th and addtonal wok at: http://common.eau.edu/na Recommended

More information

PHYS 705: Classical Mechanics. Derivation of Lagrange Equations from D Alembert s Principle

PHYS 705: Classical Mechanics. Derivation of Lagrange Equations from D Alembert s Principle 1 PHYS 705: Classcal Mechancs Devaton of Lagange Equatons fom D Alembet s Pncple 2 D Alembet s Pncple Followng a smla agument fo the vtual dsplacement to be consstent wth constants,.e, (no vtual wok fo

More information

For now, let us focus on a specific model of neurons. These are simplified from reality but can achieve remarkable results.

For 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 information

Monte Carlo comparison of back-propagation, conjugate-gradient, and finite-difference training algorithms for multilayer perceptrons

Monte Carlo comparison of back-propagation, conjugate-gradient, and finite-difference training algorithms for multilayer perceptrons Rocheste Insttute of Technology RIT Schola Woks Theses Thess/Dssetaton Collectons 20 Monte Calo compason of back-popagaton, conugate-gadent, and fnte-dffeence tanng algothms fo multlaye peceptons Stephen

More information

Chapter 11. Supplemental Text Material. The method of steepest ascent can be derived as follows. Suppose that we have fit a firstorder

Chapter 11. Supplemental Text Material. The method of steepest ascent can be derived as follows. Suppose that we have fit a firstorder S-. The Method of Steepet cent Chapter. Supplemental Text Materal The method of teepet acent can be derved a follow. Suppoe that we have ft a frtorder model y = β + β x and we wh to ue th model to determne

More information

Root Locus Techniques

Root Locus Techniques Root Locu Technque ELEC 32 Cloed-Loop Control The control nput u t ynthezed baed on the a pror knowledge of the ytem plant, the reference nput r t, and the error gnal, e t The control ytem meaure the output,

More information

(8) Gain Stage and Simple Output Stage

(8) Gain Stage and Simple Output Stage EEEB23 Electoncs Analyss & Desgn (8) Gan Stage and Smple Output Stage Leanng Outcome Able to: Analyze an example of a gan stage and output stage of a multstage amplfe. efeence: Neamen, Chapte 11 8.0) ntoducton

More information

6.6 The Marquardt Algorithm

6.6 The Marquardt Algorithm 6.6 The Mqudt Algothm lmttons of the gdent nd Tylo expnson methods ecstng the Tylo expnson n tems of ch-sque devtves ecstng the gdent sech nto n tetve mtx fomlsm Mqudt's lgothm utomtclly combnes the gdent

More information

Integral Vector Operations and Related Theorems Applications in Mechanics and E&M

Integral Vector Operations and Related Theorems Applications in Mechanics and E&M Dola Bagayoko (0) Integal Vecto Opeatons and elated Theoems Applcatons n Mechancs and E&M Ι Basc Defnton Please efe to you calculus evewed below. Ι, ΙΙ, andιιι notes and textbooks fo detals on the concepts

More information

Chapter Fifiteen. Surfaces Revisited

Chapter Fifiteen. Surfaces Revisited Chapte Ffteen ufaces Revsted 15.1 Vecto Descpton of ufaces We look now at the vey specal case of functons : D R 3, whee D R s a nce subset of the plane. We suppose s a nce functon. As the pont ( s, t)

More information

CFAR BI DETECTOR IN BINOMIAL DISTRIBUTION PULSE JAMMING 1. I. Garvanov. (Submitted by Academician Ivan Popchev on June 23, 2003)

CFAR BI DETECTOR IN BINOMIAL DISTRIBUTION PULSE JAMMING 1. I. Garvanov. (Submitted by Academician Ivan Popchev on June 23, 2003) FA BI EEO I BIOMIAL ISIBUIO PULSE JAMMIG I. Gavanov (Submtted by Academcan Ivan Popchev on June 3, 3) Abtact: In many pactcal tuaton, howeve, the envonment peence of tong pule ammng (PJ) wth hgh ntenty;

More information

Small signal analysis

Small signal analysis Small gnal analy. ntroducton Let u conder the crcut hown n Fg., where the nonlnear retor decrbed by the equaton g v havng graphcal repreentaton hown n Fg.. ( G (t G v(t v Fg. Fg. a D current ource wherea

More information

MULTILAYER PERCEPTRONS

MULTILAYER PERCEPTRONS Last updated: Nov 26, 2012 MULTILAYER PERCEPTRONS Outline 2 Combining Linea Classifies Leaning Paametes Outline 3 Combining Linea Classifies Leaning Paametes Implementing Logical Relations 4 AND and OR

More information

INTRODUCTION. consider the statements : I there exists x X. f x, such that. II there exists y Y. such that g y

INTRODUCTION. consider the statements : I there exists x X. f x, such that. II there exists y Y. such that g y INRODUCION hs dssetaton s the eadng of efeences [1], [] and [3]. Faas lemma s one of the theoems of the altenatve. hese theoems chaacteze the optmalt condtons of seveal mnmzaton poblems. It s nown that

More information

Scalars and Vectors Scalar

Scalars and Vectors Scalar Scalas and ectos Scala A phscal quantt that s completel chaacteed b a eal numbe (o b ts numecal value) s called a scala. In othe wods a scala possesses onl a magntude. Mass denst volume tempeatue tme eneg

More information

Supervised Learning. Neural Networks and Back-Propagation Learning. Credit Assignment Problem. Feedforward Network. Adaptive System.

Supervised Learning. Neural Networks and Back-Propagation Learning. Credit Assignment Problem. Feedforward Network. Adaptive System. Part 7: Neura Networ & earnng /2/05 Superved earnng Neura Networ and Bac-Propagaton earnng Produce dered output for tranng nput Generaze reaonaby & appropratey to other nput Good exampe: pattern recognton

More information

Characterizations of Slant Helices. According to Quaternionic Frame

Characterizations of Slant Helices. According to Quaternionic Frame Appled Mathematcal Scence, Vol. 7, 0, no. 75, 79-78 HIKARI Ltd, www.m-hka.com http://dx.do.og/0.988/am.0.557 Chaactezaton of Slant Helce Accodng to Quatenonc Fame Hüeyn KOCAYİĞİT and Beyza Betül PEKACAR

More information

Inference for A One Way Factorial Experiment. By Ed Stanek and Elaine Puleo

Inference for A One Way Factorial Experiment. By Ed Stanek and Elaine Puleo Infeence fo A One Way Factoial Expeiment By Ed Stanek and Elaine Puleo. Intoduction We develop etimating equation fo Facto Level mean in a completely andomized one way factoial expeiment. Thi development

More information

Machine Learning 4771

Machine Learning 4771 Machne Leanng 4771 Instucto: Tony Jebaa Topc 6 Revew: Suppot Vecto Machnes Pmal & Dual Soluton Non-sepaable SVMs Kenels SVM Demo Revew: SVM Suppot vecto machnes ae (n the smplest case) lnea classfes that

More information

Ch. 3: Forward and Inverse Kinematics

Ch. 3: Forward and Inverse Kinematics Ch. : Fowa an Invee Knemat Reap: The Denavt-Hatenbeg (DH) Conventon Repeentng eah nvual homogeneou tanfomaton a the pout of fou ba tanfomaton: pout of fou ba tanfomaton: x a x z z a a a Rot Tan Tan Rot

More information

CHAPTER 4 TWO-COMMODITY CONTINUOUS REVIEW INVENTORY SYSTEM WITH BULK DEMAND FOR ONE COMMODITY

CHAPTER 4 TWO-COMMODITY CONTINUOUS REVIEW INVENTORY SYSTEM WITH BULK DEMAND FOR ONE COMMODITY Unvety of Petoa etd Van choo C de Wet 6 CHAPTER 4 TWO-COMMODITY CONTINUOU REVIEW INVENTORY YTEM WITH BULK DEMAND FOR ONE COMMODITY A modfed veon of th chapte ha been accepted n Aa-Pacfc Jounal of Opeatonal

More information

EEE 241: Linear Systems

EEE 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 information

Machine Learning. Spectral Clustering. Lecture 23, April 14, Reading: Eric Xing 1

Machine Learning. Spectral Clustering. Lecture 23, April 14, Reading: Eric Xing 1 Machne Leanng -7/5 7/5-78, 78, Spng 8 Spectal Clusteng Ec Xng Lectue 3, pl 4, 8 Readng: Ec Xng Data Clusteng wo dffeent ctea Compactness, e.g., k-means, mxtue models Connectvty, e.g., spectal clusteng

More information

4 SingularValue Decomposition (SVD)

4 SingularValue Decomposition (SVD) /6/00 Z:\ jeh\self\boo Kannan\Jan-5-00\4 SVD 4 SngulaValue Decomposton (SVD) Chapte 4 Pat SVD he sngula value decomposton of a matx s the factozaton of nto the poduct of thee matces = UDV whee the columns

More information

CHAPTER 10: LINEAR DISCRIMINATION

CHAPTER 10: LINEAR DISCRIMINATION HAPER : LINEAR DISRIMINAION Dscmnan-based lassfcaon 3 In classfcaon h K classes ( k ) We defned dsmnan funcon g () = K hen gven an es eample e chose (pedced) s class label as f g () as he mamum among g

More information

Value Prediction with FA. Chapter 8: Generalization and Function Approximation. Adapt Supervised Learning Algorithms. Backups as Training Examples [ ]

Value Prediction with FA. Chapter 8: Generalization and Function Approximation. Adapt Supervised Learning Algorithms. Backups as Training Examples [ ] Chapte 8: Genealization and Function Appoximation Objectives of this chapte:! Look at how expeience with a limited pat of the state set be used to poduce good behavio ove a much lage pat.! Oveview of function

More information

A. Thicknesses and Densities

A. Thicknesses and Densities 10 Lab0 The Eath s Shells A. Thcknesses and Denstes Any theoy of the nteo of the Eath must be consstent wth the fact that ts aggegate densty s 5.5 g/cm (ecall we calculated ths densty last tme). In othe

More information

Chapter 8: Generalization and Function Approximation

Chapter 8: Generalization and Function Approximation Chapte 8: Genealization and Function Appoximation Objectives of this chapte: Look at how expeience with a limited pat of the state set be used to poduce good behavio ove a much lage pat. Oveview of function

More information

Queuing Network Approximation Technique for Evaluating Performance of Computer Systems with Input to Terminals

Queuing Network Approximation Technique for Evaluating Performance of Computer Systems with Input to Terminals 6th Intenatonal Confeence on Chemcal Agcultual Envonmental and Bologcal cence CAEB-7 Dec. 7-8 07 Pa Fance ueung Netwo Appoxmaton Technque fo Evaluatng Pefomance of Compute ytem wth Input to Temnal Ha Yoh

More information

Cohen Macaulay Rings Associated with Digraphs

Cohen Macaulay Rings Associated with Digraphs JOURNAL OF ALGEBRA 206, 541554 1998 ARTICLE NO. JA987449 CohenMacaulay Rng Aocated wth Dgaph Kazufum Eto Depatment of Mathematc, Nppon Inttute of Technology, Satama, Japan Communcated by Cag Hunee Receved

More information

Review of Vector Algebra and Vector Calculus Operations

Review of Vector Algebra and Vector Calculus Operations Revew of Vecto Algeba and Vecto Calculus Opeatons Tpes of vaables n Flud Mechancs Repesentaton of vectos Dffeent coodnate sstems Base vecto elatons Scala and vecto poducts Stess Newton s law of vscost

More information

LINEAR MOMENTUM. product of the mass m and the velocity v r of an object r r

LINEAR MOMENTUM. product of the mass m and the velocity v r of an object r r LINEAR MOMENTUM Imagne beng on a skateboad, at est that can move wthout cton on a smooth suace You catch a heavy, slow-movng ball that has been thown to you you begn to move Altenatvely you catch a lght,

More information

Multilayer neural networks

Multilayer 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 information

9/12/2013. Microelectronics Circuit Analysis and Design. Modes of Operation. Cross Section of Integrated Circuit npn Transistor

9/12/2013. Microelectronics Circuit Analysis and Design. Modes of Operation. Cross Section of Integrated Circuit npn Transistor Mcoelectoncs Ccut Analyss and Desgn Donald A. Neamen Chapte 5 The pola Juncton Tanssto In ths chapte, we wll: Dscuss the physcal stuctue and opeaton of the bpola juncton tanssto. Undestand the dc analyss

More information

REDUCTION MODULO p. We will prove the reduction modulo p theorem in the general form as given by exercise 4.12, p. 143, of [1].

REDUCTION MODULO p. We will prove the reduction modulo p theorem in the general form as given by exercise 4.12, p. 143, of [1]. REDUCTION MODULO p. IAN KIMING We wll prove the reducton modulo p theorem n the general form as gven by exercse 4.12, p. 143, of [1]. We consder an ellptc curve E defned over Q and gven by a Weerstraß

More information

Test 1 phy What mass of a material with density ρ is required to make a hollow spherical shell having inner radius r i and outer radius r o?

Test 1 phy What mass of a material with density ρ is required to make a hollow spherical shell having inner radius r i and outer radius r o? Test 1 phy 0 1. a) What s the pupose of measuement? b) Wte all fou condtons, whch must be satsfed by a scala poduct. (Use dffeent symbols to dstngush opeatons on ectos fom opeatons on numbes.) c) What

More information

V. Principles of Irreversible Thermodynamics. s = S - S 0 (7.3) s = = - g i, k. "Flux": = da i. "Force": = -Â g a ik k = X i. Â J i X i (7.

V. Principles of Irreversible Thermodynamics. s = S - S 0 (7.3) s = = - g i, k. Flux: = da i. Force: = -Â g a ik k = X i. Â J i X i (7. Themodynamcs and Knetcs of Solds 71 V. Pncples of Ievesble Themodynamcs 5. Onsage s Teatment s = S - S 0 = s( a 1, a 2,...) a n = A g - A n (7.6) Equlbum themodynamcs detemnes the paametes of an equlbum

More information

UNIT10 PLANE OF REGRESSION

UNIT10 PLANE OF REGRESSION UIT0 PLAE OF REGRESSIO Plane of Regesson Stuctue 0. Intoducton Ojectves 0. Yule s otaton 0. Plane of Regesson fo thee Vaales 0.4 Popetes of Resduals 0.5 Vaance of the Resduals 0.6 Summay 0.7 Solutons /

More information

Chapter I Matrices, Vectors, & Vector Calculus 1-1, 1-9, 1-10, 1-11, 1-17, 1-18, 1-25, 1-27, 1-36, 1-37, 1-41.

Chapter I Matrices, Vectors, & Vector Calculus 1-1, 1-9, 1-10, 1-11, 1-17, 1-18, 1-25, 1-27, 1-36, 1-37, 1-41. Chapte I Matces, Vectos, & Vecto Calculus -, -9, -0, -, -7, -8, -5, -7, -36, -37, -4. . Concept of a Scala Consde the aa of patcles shown n the fgue. he mass of the patcle at (,) can be epessed as. M (,

More information

Determining the Best Linear Unbiased Predictor of PSU Means with the Data. included with the Random Variables. Ed Stanek

Determining the Best Linear Unbiased Predictor of PSU Means with the Data. included with the Random Variables. Ed Stanek Detemining te Bet Linea Unbiaed Pedicto of PSU ean wit te Data included wit te andom Vaiable Ed Stanek Intoduction We develop te equation fo te bet linea unbiaed pedicto of PSU mean in a two tage andom

More information

ˆ x ESTIMATOR. state vector estimate

ˆ x ESTIMATOR. state vector estimate hapte 9 ontolle Degn wo Independent Step: Feedback Degn ontol Law =- ame all tate ae acceble a lot of eno ae necea Degn of Etmato alo called an Obeve whch etmate the ente tate vecto gven the otpt and npt

More information

Chapter 6 The Effect of the GPS Systematic Errors on Deformation Parameters

Chapter 6 The Effect of the GPS Systematic Errors on Deformation Parameters Chapter 6 The Effect of the GPS Sytematc Error on Deformaton Parameter 6.. General Beutler et al., (988) dd the frt comprehenve tudy on the GPS ytematc error. Baed on a geometrc approach and aumng a unform

More information

Energy in Closed Systems

Energy in Closed Systems Enegy n Closed Systems Anamta Palt palt.anamta@gmal.com Abstact The wtng ndcates a beakdown of the classcal laws. We consde consevaton of enegy wth a many body system n elaton to the nvese squae law and

More information

Engineering Mechanics. Force resultants, Torques, Scalar Products, Equivalent Force systems

Engineering Mechanics. Force resultants, Torques, Scalar Products, Equivalent Force systems Engneeng echancs oce esultants, Toques, Scala oducts, Equvalent oce sstems Tata cgaw-hll Companes, 008 Resultant of Two oces foce: acton of one bod on anothe; chaacteed b ts pont of applcaton, magntude,

More information

Excellent web site with information on various methods and numerical codes for scattering by nonspherical particles:

Excellent web site with information on various methods and numerical codes for scattering by nonspherical particles: Lectue 5. Lght catteng and abopton by atmophec patcuate. at 3: Scatteng and abopton by nonpheca patce: Ray-tacng, T- Matx, and FDTD method. Objectve:. Type of nonpheca patce n the atmophee.. Ray-tacng

More information

2/24/2014. The point mass. Impulse for a single collision The impulse of a force is a vector. The Center of Mass. System of particles

2/24/2014. The point mass. Impulse for a single collision The impulse of a force is a vector. The Center of Mass. System of particles /4/04 Chapte 7 Lnea oentu Lnea oentu of a Sngle Patcle Lnea oentu: p υ It s a easue of the patcle s oton It s a vecto, sla to the veloct p υ p υ p υ z z p It also depends on the ass of the object, sla

More information

From Biot-Savart Law to Divergence of B (1)

From Biot-Savart Law to Divergence of B (1) From Bot-Savart Law to Dvergence of B (1) Let s prove that Bot-Savart gves us B (r ) = 0 for an arbtrary current densty. Frst take the dvergence of both sdes of Bot-Savart. The dervatve s wth respect to

More information

Electrical Circuits II (ECE233b)

Electrical Circuits II (ECE233b) Electrcal Crcut II (ECE33b) Applcaton of Laplace Tranform to Crcut Analy Anet Dounav The Unverty of Wetern Ontaro Faculty of Engneerng Scence Crcut Element Retance Tme Doman (t) v(t) R v(t) = R(t) Frequency

More information

Multilayer Perceptrons and Backpropagation. Perceptrons. Recap: Perceptrons. Informatics 1 CG: Lecture 6. Mirella Lapata

Multilayer 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 information

Clustering gene expression data & the EM algorithm

Clustering gene expression data & the EM algorithm CG, Fall 2011-12 Clusterng gene expresson data & the EM algorthm CG 08 Ron Shamr 1 How Gene Expresson Data Looks Entres of the Raw Data matrx: Rato values Absolute values Row = gene s expresson pattern

More information

ECE Spring Prof. David R. Jackson ECE Dept. Notes 5

ECE Spring Prof. David R. Jackson ECE Dept. Notes 5 ECE 634 Sping 06 Pof. David R. Jacson ECE Dept. Notes 5 TM x Sface-Wave Soltion Poblem nde consideation: x h ε, µ z A TM x sface wave is popagating in the z diection (no y vaiation). TM x Sface-Wave Soltion

More information

Using DP for hierarchical discretization of continuous attributes. Amit Goyal (31 st March 2008)

Using DP for hierarchical discretization of continuous attributes. Amit Goyal (31 st March 2008) Usng DP fo heachcal dscetzaton of contnos attbtes Amt Goyal 31 st Mach 2008 Refeence Chng-Cheng Shen and Yen-Lang Chen. A dynamc-pogammng algothm fo heachcal dscetzaton of contnos attbtes. In Eopean Jonal

More information

Variable Structure Control ~ Basics

Variable Structure Control ~ Basics Varable Structure Control ~ Bac Harry G. Kwatny Department of Mechancal Engneerng & Mechanc Drexel Unverty Outlne A prelmnary example VS ytem, ldng mode, reachng Bac of dcontnuou ytem Example: underea

More information

PHY126 Summer Session I, 2008

PHY126 Summer Session I, 2008 PHY6 Summe Sesson I, 8 Most of nfomaton s avalable at: http://nngoup.phscs.sunsb.edu/~chak/phy6-8 ncludng the sllabus and lectue sldes. Read sllabus and watch fo mpotant announcements. Homewok assgnment

More information

Simulation of Spatially Correlated Large-Scale Parameters and Obtaining Model Parameters from Measurements

Simulation of Spatially Correlated Large-Scale Parameters and Obtaining Model Parameters from Measurements Simulation of Spatially Coelated Lage-Scale Paamete and Obtaining Model Paamete fom PER ZETTERBERG Stockholm Septembe 8 TRITA EE 8:49 Simulation of Spatially Coelated Lage-Scale Paamete and Obtaining Model

More information

APPLICATIONS OF SEMIGENERALIZED -CLOSED SETS

APPLICATIONS OF SEMIGENERALIZED -CLOSED SETS Intenatonal Jounal of Mathematcal Engneeng Scence ISSN : 22776982 Volume Issue 4 (Apl 202) http://www.mes.com/ https://stes.google.com/ste/mesounal/ APPLICATIONS OF SEMIGENERALIZED CLOSED SETS G.SHANMUGAM,

More information

Randomized Complexity Classes

Randomized Complexity Classes Randomized Complexity Classes We allow TM to toss coins/thow dice etc. We wite M(x,R) fo output of M on input x, coin tosses R Def: L R poly-time andomized M : x L => R [M(x,R)=1] 1/ x L => R [M(x,R)=1]

More information

Error Bars in both X and Y

Error Bars in both X and Y Error Bars n both X and Y Wrong ways to ft a lne : 1. y(x) a x +b (σ x 0). x(y) c y + d (σ y 0) 3. splt dfference between 1 and. Example: Prmordal He abundance: Extrapolate ft lne to [ O / H ] 0. [ He

More information

The Forming Theory and the NC Machining for The Rotary Burs with the Spectral Edge Distribution

The Forming Theory and the NC Machining for The Rotary Burs with the Spectral Edge Distribution oden Appled Scence The Fomn Theoy and the NC achnn fo The Rotay us wth the Spectal Ede Dstbuton Huan Lu Depatment of echancal Enneen, Zhejan Unvesty of Scence and Technoloy Hanzhou, c.y. chan, 310023,

More information

Outline and Reading. Dynamic Programming. Dynamic Programming revealed. Computing Fibonacci. The General Dynamic Programming Technique

Outline and Reading. Dynamic Programming. Dynamic Programming revealed. Computing Fibonacci. The General Dynamic Programming Technique Outlne and Readng Dynamc Programmng The General Technque ( 5.3.2) -1 Knapsac Problem ( 5.3.3) Matrx Chan-Product ( 5.3.1) Dynamc Programmng verson 1.4 1 Dynamc Programmng verson 1.4 2 Dynamc Programmng

More information

Part V: Velocity and Acceleration Analysis of Mechanisms

Part V: Velocity and Acceleration Analysis of Mechanisms Pat V: Velocty an Acceleaton Analyss of Mechansms Ths secton wll evew the most common an cuently pactce methos fo completng the knematcs analyss of mechansms; escbng moton though velocty an acceleaton.

More information

Problem #1. Known: All required parameters. Schematic: Find: Depth of freezing as function of time. Strategy:

Problem #1. Known: All required parameters. Schematic: Find: Depth of freezing as function of time. Strategy: BEE 3500 013 Prelm Soluton Problem #1 Known: All requred parameter. Schematc: Fnd: Depth of freezng a functon of tme. Strategy: In thee mplfed analy for freezng tme, a wa done n cla for a lab geometry,

More information

1 cos. where v v sin. Range Equations: for an object that lands at the same height at which it starts. v sin 2 i. t g. and. sin g

1 cos. where v v sin. Range Equations: for an object that lands at the same height at which it starts. v sin 2 i. t g. and. sin g SPH3UW Unt.5 Projectle Moton Pae 1 of 10 Note Phc Inventor Parabolc Moton curved oton n the hape of a parabola. In the drecton, the equaton of oton ha a t ter Projectle Moton the parabolc oton of an object,

More information

Rigid Bodies: Equivalent Systems of Forces

Rigid Bodies: Equivalent Systems of Forces Engneeng Statcs, ENGR 2301 Chapte 3 Rgd Bodes: Equvalent Sstems of oces Intoducton Teatment of a bod as a sngle patcle s not alwas possble. In geneal, the se of the bod and the specfc ponts of applcaton

More information

Physics 11b Lecture #2. Electric Field Electric Flux Gauss s Law

Physics 11b Lecture #2. Electric Field Electric Flux Gauss s Law Physcs 11b Lectue # Electc Feld Electc Flux Gauss s Law What We Dd Last Tme Electc chage = How object esponds to electc foce Comes n postve and negatve flavos Conseved Electc foce Coulomb s Law F Same

More information

Optimization Methods: Linear Programming- Revised Simplex Method. Module 3 Lecture Notes 5. Revised Simplex Method, Duality and Sensitivity analysis

Optimization Methods: Linear Programming- Revised Simplex Method. Module 3 Lecture Notes 5. Revised Simplex Method, Duality and Sensitivity analysis Optmzaton Meods: Lnea Pogammng- Revsed Smple Meod Module Lectue Notes Revsed Smple Meod, Dualty and Senstvty analyss Intoducton In e pevous class, e smple meod was dscussed whee e smple tableau at each

More information

Experimental study on parameter choices in norm-r support vector regression machines with noisy input

Experimental study on parameter choices in norm-r support vector regression machines with noisy input Soft Comput 006) 0: 9 3 DOI 0.007/s00500-005-0474-z ORIGINAL PAPER S. Wang J. Zhu F. L. Chung Hu Dewen Expemental study on paamete choces n nom- suppot vecto egesson machnes wth nosy nput Publshed onlne:

More information

4/18/2005. Statistical Learning Theory

4/18/2005. Statistical Learning Theory Statistical Leaning Theoy Statistical Leaning Theoy A model of supevised leaning consists of: a Envionment - Supplying a vecto x with a fixed but unknown pdf F x (x b Teache. It povides a desied esponse

More information

Week 5: Neural Networks

Week 5: Neural Networks Week 5: Neural Networks Instructor: Sergey Levne Neural Networks Summary In the prevous lecture, we saw how we can construct neural networks by extendng logstc regresson. Neural networks consst of multple

More information

Logistic Classifier CISC 5800 Professor Daniel Leeds

Logistic Classifier CISC 5800 Professor Daniel Leeds lon 9/7/8 Logstc Classfer CISC 58 Professor Danel Leeds Classfcaton strategy: generatve vs. dscrmnatve Generatve, e.g., Bayes/Naïve Bayes: 5 5 Identfy probablty dstrbuton for each class Determne class

More information

Scattering of two identical particles in the center-of. of-mass frame. (b)

Scattering of two identical particles in the center-of. of-mass frame. (b) Lecture # November 5 Scatterng of two dentcal partcle Relatvtc Quantum Mechanc: The Klen-Gordon equaton Interpretaton of the Klen-Gordon equaton The Drac equaton Drac repreentaton for the matrce α and

More information

DYNAMICS VECTOR MECHANICS FOR ENGINEERS: Kinematics of Rigid Bodies in Three Dimensions. Seventh Edition CHAPTER

DYNAMICS VECTOR MECHANICS FOR ENGINEERS: Kinematics of Rigid Bodies in Three Dimensions. Seventh Edition CHAPTER Edton CAPTER 8 VECTOR MECANCS FOR ENGNEERS: DYNAMCS Fednand P. Bee E. Russell Johnston, J. Lectue Notes: J. Walt Ole Teas Tech Unvest Knematcs of Rgd Bodes n Thee Dmensons 003 The McGaw-ll Companes, nc.

More information

Specification -- Assumptions of the Simple Classical Linear Regression Model (CLRM) 1. Introduction

Specification -- Assumptions of the Simple Classical Linear Regression Model (CLRM) 1. Introduction ECONOMICS 35* -- NOTE ECON 35* -- NOTE Specfcaton -- Aumpton of the Smple Clacal Lnear Regreon Model (CLRM). Introducton CLRM tand for the Clacal Lnear Regreon Model. The CLRM alo known a the tandard lnear

More information

Multi-layer neural networks

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 information

Statistical Properties of the OLS Coefficient Estimators. 1. Introduction

Statistical Properties of the OLS Coefficient Estimators. 1. Introduction ECOOMICS 35* -- OTE 4 ECO 35* -- OTE 4 Stattcal Properte of the OLS Coeffcent Etmator Introducton We derved n ote the OLS (Ordnary Leat Square etmator ˆβ j (j, of the regreon coeffcent βj (j, n the mple

More information

Physics 201 Lecture 4

Physics 201 Lecture 4 Phscs 1 Lectue 4 ltoda: hapte 3 Lectue 4 v Intoduce scalas and vectos v Peom basc vecto aleba (addton and subtacton) v Inteconvet between atesan & Pola coodnates Stat n nteestn 1D moton poblem: ace 9.8

More information

P 365. r r r )...(1 365

P 365. r r r )...(1 365 SCIENCE WORLD JOURNAL VOL (NO4) 008 www.scecncewoldounal.og ISSN 597-64 SHORT COMMUNICATION ANALYSING THE APPROXIMATION MODEL TO BIRTHDAY PROBLEM *CHOJI, D.N. & DEME, A.C. Depatment of Mathematcs Unvesty

More information

TRAVELING WAVES. Chapter Simple Wave Motion. Waves in which the disturbance is parallel to the direction of propagation are called the

TRAVELING WAVES. Chapter Simple Wave Motion. Waves in which the disturbance is parallel to the direction of propagation are called the Chapte 15 RAVELING WAVES 15.1 Simple Wave Motion Wave in which the ditubance i pependicula to the diection of popagation ae called the tanvee wave. Wave in which the ditubance i paallel to the diection

More information

THE REGRESSION MODEL OF TRANSMISSION LINE ICING BASED ON NEURAL NETWORKS

THE REGRESSION MODEL OF TRANSMISSION LINE ICING BASED ON NEURAL NETWORKS The 4th Intenatonal Wokshop on Atmosphec Icng of Stuctues, Chongqng, Chna, May 8 - May 3, 20 THE REGRESSION MODEL OF TRANSMISSION LINE ICING BASED ON NEURAL NETWORKS Sun Muxa, Da Dong*, Hao Yanpeng, Huang

More information

Additional File 1 - Detailed explanation of the expression level CPD

Additional File 1 - Detailed explanation of the expression level CPD Addtonal Fle - Detaled explanaton of the expreon level CPD A mentoned n the man text, the man CPD for the uterng model cont of two ndvdual factor: P( level gen P( level gen P ( level gen 2 (.).. CPD factor

More information

Summer Workshop on the Reaction Theory Exercise sheet 8. Classwork

Summer Workshop on the Reaction Theory Exercise sheet 8. Classwork Joned Physcs Analyss Cente Summe Wokshop on the Reacton Theoy Execse sheet 8 Vncent Matheu Contact: http://www.ndana.edu/~sst/ndex.html June June To be dscussed on Tuesday of Week-II. Classwok. Deve all

More information

Capítulo. Three Dimensions

Capítulo. Three Dimensions Capítulo Knematcs of Rgd Bodes n Thee Dmensons Mecánca Contents ntoducton Rgd Bod Angula Momentum n Thee Dmensons Pncple of mpulse and Momentum Knetc Eneg Sample Poblem 8. Sample Poblem 8. Moton of a Rgd

More information

CS649 Sensor Networks IP Track Lecture 3: Target/Source Localization in Sensor Networks

CS649 Sensor Networks IP Track Lecture 3: Target/Source Localization in Sensor Networks C649 enso etwoks IP Tack Lectue 3: Taget/ouce Localaton n enso etwoks I-Jeng Wang http://hng.cs.jhu.edu/wsn06/ png 006 C 649 Taget/ouce Localaton n Weless enso etwoks Basc Poblem tatement: Collaboatve

More information

Implementation of RCWA

Implementation of RCWA Instucto D. Ramond Rumpf (915) 747 6958 cumpf@utep.edu EE 5337 Computational Electomagnetics Lectue # Implementation of RCWA Lectue These notes ma contain copighted mateial obtained unde fai use ules.

More information

Compact Representation of Continuous Energy Surfaces for More Efficient Protein Design

Compact Representation of Continuous Energy Surfaces for More Efficient Protein Design pub.ac.og/jctc Compact Repeentaton of Contnuou Enegy Suface fo Moe Effcent Poten Degn Mak A. Hallen,, Pablo Ganza, and Buce R. Donald*,,, Depatment of Compute Scence and Depatment of Chemty, Duke Unvety,

More information

An Approach to Inverse Fuzzy Arithmetic

An Approach to Inverse Fuzzy Arithmetic An Appoach to Invese Fuzzy Athmetc Mchael Hanss Insttute A of Mechancs, Unvesty of Stuttgat Stuttgat, Gemany mhanss@mechaun-stuttgatde Abstact A novel appoach of nvese fuzzy athmetc s ntoduced to successfully

More information

Rotating Disk Electrode -a hydrodynamic method

Rotating Disk Electrode -a hydrodynamic method Rotatng Dsk Electode -a hdodnamc method Fe Lu Ma 3, 0 ente fo Electochemcal Engneeng Reseach Depatment of hemcal and Bomolecula Engneeng Rotatng Dsk Electode A otatng dsk electode RDE s a hdodnamc wokng

More information

Harmonic oscillator approximation

Harmonic oscillator approximation armonc ocllator approxmaton armonc ocllator approxmaton Euaton to be olved We are fndng a mnmum of the functon under the retrcton where W P, P,..., P, Q, Q,..., Q P, P,..., P, Q, Q,..., Q lnwgner functon

More information

19 The Born-Oppenheimer Approximation

19 The Born-Oppenheimer Approximation 9 The Bon-Oppenheme Appoxmaton The full nonelatvstc Hamltonan fo a molecule s gven by (n a.u.) Ĥ = A M A A A, Z A + A + >j j (883) Lets ewte the Hamltonan to emphasze the goal as Ĥ = + A A A, >j j M A

More information

1 Input-Output Mappings. 2 Hebbian Failure. 3 Delta Rule Success.

1 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 information