ࡱ> g Rq%bjbjVVsr<r<qYYYYYmmmmDmFzzzFFFFFFF$HTK4AF!YzX"zzzAFYYbFzYYEzF@0EDe*hA$mExF0FB@K~*KHEDED\KYDzzzzzzzAFAFzzzFzzzzKzzzzzzzzz/ : -NWS"~?el'Yf[ zYef['Y~ Course Syllabus of Zhongnan University of Economics and Law Course Title: Machine LearningCourse Code41143016SemesterSpringTeaching Hours48Credits3PrerequisitesSolid mathematical background, equivalent to a 1-semester undergraduate course in each of the following: linear algebra, multivariate differential calculus, probability theory, and statistics. Python programming required for most homework assignments. Computer science background up to a "data structures and algorithms" course.Instructor InformationNameXIA SongEmail HYPERLINK "mailto:24678790@qq.com" 24678790@qq.com InstituteSchool of Information and Safety EngineeringApplicable ObjectInternational StudentsCourse Objectives Understand the Concepts, Techniques and Mathematical Frameworks Used by Experts in Machine Learning Visualize data to understand relationships and assess data quality Apply linear algebra, statistics, and optimization techniques to create machine learning algorithms Understand engineering and business objectives to plan applications Assess data information content and predictive capability Detect overfitting and implement strategies to improve prediction Master the use of machine learning packages with understanding of how hyperparameters can be adjusted to improve performance Understand the differences between classification, regression, and clustering and when each can be applied Communicate machine learning decisions with uncertainty quantification Implement machine learning techniques successfully to complete a group project Course Description (200 words) Theory of machine learning with engineering applications. Machine learning is a convergence of linear algebra, statistics, optimization, and computational methods to allow computers to make decisions and take action from data. Examples of machine learning are now pervasive and are expected to further influence transportation, entertainment, retail, and energy industries. This engineering course reviews theory and applications of machine learning to engineering applications with a survey of unsupervised and supervised learning methods. The course combines mathematical details with several case studies that provide an intuition for machine learning with methods for classification, regression, and dimensionality reduction. A second phase of the course is a hands-on group project. The engineering problems and theory will guide the student towards a working fluency in state-of-the-art methods implemented in Python. Assessment Methods Your final grade will be determined by your performance on the various aspects of the class: Homework: 25%, assessed on your individual submissions. We will drop the lowest homework grade. Project: 70%, assessed on meeting the project criteria and your peer assessment. The 70% is split between the two milestones and the proposal. 10% are assigned to the proposal, 20% are assigned to your first milestone, 40% to your final submission. Group Activities: 5%, 1% for each activity. We will evaluate your work holistically beyond mechanical correctness and focus on the overall quality of the work. Textbooks and References Textbooks Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2, 3rd Edition, Packt Publishing, 2019 References The Elements of Statistical Learning (Hastie, Friedman, and Tibshirani) Pattern Recognition and Machine Learning (Christopher Bishop) Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition (Aurlien Gron) Course planningChapter 1Giving Computers the Ability to Learn from Data Building intelligent machines to transform data into knowledge The three different types of machine learning Introduction to the basic terminology and notations A roadmap for building machine learning systems Using Python for machine learning Chapter 2 Training Simple Machine Learning Algorithms for Classification Artificial neurons a brief glimpse into the early history of machine learning Implementing a perceptron learning algorithm in Python Adaptive linear neurons and the convergence of learning Chapter 3A Tour of Machine Learning Classifiers Using scikit-learn First steps with scikit-learn training a perceptron Modeling class probabilities via logistic regression Maximum margin classification with support vector machines Solving nonlinear problems using a kernel SVM Decision tree learning K-nearest neighbors a lazy learning algorithm Chapter 4Building Good Training Datasets Data Preprocessing Dealing with missing data Handling categorical data Partitioning a dataset into separate training and test datasets Bringing features onto the same scale Selecting meaningful features Assessing feature importance with random forests Chapter 5Compressing Data via Dimensionality Reduction Unsupervised dimensionality reduction via principal component analysis Supervised data compression via linear discriminant analysis Using kernel principal component analysis for nonlinear mappings Chapter 6Learning Best Practices for Model Evaluation and Hyperparameter Tuning Streamlining workflows with pipelines Using k-fold cross-validation to assess model performance Debugging algorithms with learning and validation curves Fine-tuning machine learning models via grid search Looking at different performance evaluation metrics Chapter 7Combining Different Models for Ensemble Learning Learning with ensembles Combining classifiers via majority vote Bagging building an ensemble of classifiers from bootstrap samples Leveraging weak learners via adaptive boosting Chapter 8Applying Machine Learning to Sentiment Analysis Preparing the IMDb movie review data for text processing Introducing the bag-of-words model Training a logistic regression model for document classification Working with bigger data online algorithms and out-of-core learning Topic modeling with Latent Dirichlet Allocation Chapter 9Embedding a Machine Learning Model into a Web Application Serializing fitted scikit-learn estimators Setting up an SQLite database for data storage Developing a web application with Flask Turning the movie review classifier into a web application Deploying the web application to a public server Chapter 10Predicting Continuous Target Variables with Regression Analysis Introducing linear regression Exploring the Housing dataset Implementing an ordinary least squares linear regression model Fitting a robust regression model using RANSAC Evaluating the performance of linear regression models Using regularized methods for regression Turning a linear regression model into a curve polynomial regression Dealing with nonlinear relationships using random forests Chapter 11Working with Unlabeled Data Clustering Analysis Grouping objects by similarity using k-means Organizing clusters as a hierarchical tree Locating regions of high density via DBSCAN Chapter 12Implementing a Multilayer Artificial Neural Network from Scratch Modeling complex functions with artificial neural networks Classifying handwritten digits Training an artificial neural network About the convergence in neural networks A few last words about the neural network implementation      " & 8 : B D H J X Z \ ` z | ʸwj]QE]jE]jEhcw hcw 5aJo(hcw hcw 5\aJhcw h#5\aJo(hcw hcw 5\aJo(hcw h#5\aJ hcw hcw 5B*KHaJph#hcw hcw B*KH\aJo(ph#hcw h#5B*KHaJo(ph#hcw hcw 5B*KHaJo(phhcw 5CJ\aJo($hcw 5CJOJPJQJ^JaJo(+jhcw 5B*CJOJQJUaJph FgQ$$Ifa$gdcw l mkd$$IfT7(9)0644 lap ytcw T$Ifl KWD,`K WD` $WDX`a$  $ $$Ifa$gdcw l $$Ifa$gdcw l $ & D J J4$$Ifa$gdcw l $$Ifa$gdcw l kd$$IfT7\ w(d  V 0644 lap(ytcw TJ Z ^ ` kd^$$IfT7\ w(d  V 0644 lap(ytcw T$$Ifa$gdcw l $$Ifa$gdcw l ` |    Kkd1$$IfT70 (d 0644 lapytcw T$ & F$Ifa$gdcw l $$Ifa$gdcw l | ~      $ % - . 3 4 5 H W Y Z i j k m v w 竟qehcw hcw 5aJo(hcw hcw 5B*aJo(ph+++hcw hcw 5B*aJph+++hcw h \0J5\aJo(hcw h \5\aJjhcw h \5U\aJhcw h \5\aJo(#hcw hcw 5B*KHaJo(phhcw hIA5\aJo(hcw hcw 5\aJo(hcw hIA5\aJ   % . 4 l xbLbL$$Ifa$gdcw l $$Ifa$gdcw l mkd$$IfT7(9)0644 lap ytcw T$dh$1$Ifa$gdcw l l m w J4$$Ifa$gdcw l $$Ifa$gdcw l kd_$$IfT7\ w(d  V 0644 lap(ytcw T zdN$$Ifa$gdcw l $$Ifa$gdcw l kd2$$IfT70 (d 0644 lapytcw T E F G +-.46ALMNķ⷟pp^O?O?Ohcw hcw 5B*aJo(phhcw hcw 5B*aJph#hcw hcw 5B*CJaJo(ph/hcw hcw 5B*CJOJQJ^JaJo(ph,hcw hcw 5B*CJOJQJ^JaJphhcw hfq5\aJhcw hZa5\aJhcw hZa5\aJo(hcw hcw 5aJo(#hcw hcw 5B*KHaJo(phhcw hcw 5\aJo( hcw hcw B*KH\aJph F G zdTTT>> & F$Ifgdcw l $Ifl $$Ifa$gdcw l kd$$IfT70 (d 0644 lapytcw T 2 l +,-.Tkdx$$IfT70 (d 0644 lapytcw T$Ifl  & F$Ifgdcw l .AMNlm$Ifgdfql $Ifl dP$Ifgdcw l `zdTA$Ifgdfql $Ifl $$Ifa$gdcw l kd$$IfT70 (d 0644 lapytcw TjkOQqsXZ[\dtuv `a{ooohcw h>5\aJ#hcw hZa5B*KHaJo(phhcw hZa5\aJhcw hZa5\aJo(hcw hcw 5B*aJo(ph hcw hcw 5B*KHaJphhcw hfq5\aJo(hcw hfq5\aJhcw hcw 5\aJo(#hcw hcw 5B*KHaJo(ph+`YZ[\Tkd$$IfT70 (d 0644 lapytcw T$Ifl  & F$Ifgdcw l \uv a$Ifl $$Ifa$gdcw l zd$$Ifa$gdcw l kda$$IfT70 (d 0644 lapytcw TM@|iSSSSS & F$Ifgdcw l $IfgdCl $$Ifa$gdcw l mkd$$IfT7(9)0644 lap ytcw TLM?@BFGLM|}JKMQRVW}~67de{|ξίΟξξξΟξΟΟίξΟΟΟΟξίξΟhcw h[5B*aJphhcw hcw 5B*aJo(phhcw hcw 5B*aJphhcw hC5B*aJo(phhcw hC5B*aJph#hcw hcw 5B*KHaJo(ph hcw hcw 5B*KHaJph8@ABMjTA$IfgdCl $$Ifa$gdcw l kd$$IfT70 (z 0644 lapytcw T$Ifl KLMWN8$$Ifa$gdcw l kd2 $$IfT70 (z 0644 lapytcw T$$Ifa$gdcw l  & F$Ifgdcw l W7e|$$Ifa$gdcw l  & F$Ifgdcw l $IfgdCl !azdQ;;; & F$Ifgdcw l $IfgdCl $$Ifa$gdcw l kd $$IfT70 (z 0644 lapytcw T !CDVW()NO)+,45~l~l#hcw heh5B*KHaJo(ph hcw heh5B*KHaJphhcw heh5B*aJo(phhcw heh5B*aJph#hcw hcw 5B*KHaJo(ph hcw hcw 5B*KHaJphhcw hcw 5B*aJphhcw h[5B*aJphhcw hcw 5B*aJo(ph*aN8$$Ifa$gdcw l kdx $$IfT70 (z 0644 lapytcw T$$Ifa$gdcw l  & F$Ifgdcw l W>kd $$IfT70 (z 0644 lapytcw T$$Ifa$gdcw l  & F$Ifgdcw l $Ifl )O*+$ & F $Ifa$gdcw l $$Ifa$gdcw l +,6hzddKKKKd$ & F $Ifa$gdcw l $$Ifa$gdcw l kd $$IfT70 (z 0644 lapytcw T56gh&'(WX% & : ; j k l m w 3!4!n!o!!!!!!!!!! " "(")"g"h"*#+#@#A#z#{#|#}######$$=$>$?$@$#hcw heh5B*KHaJo(phhcw heh5B*aJo(phhcw heh5B*aJph hcw heh5B*KHaJphK(X; k zddKKKKK$ & F $Ifa$gdcw l $$Ifa$gdcw l kda $$IfT70 (z 0644 lapytcw Tk l m w !4!o!dKKKK$ & F $Ifa$gdcw l kd $$IfT70 (z 0644 lapytcw T$$Ifa$gdcw l o!!!!!!Kkd $$IfT70 (z 0644 lapytcw T$$Ifa$gdcw l $ & F $Ifa$gdcw l ! ")"h""""A#{#|#$$Ifa$gdcw l $ & F $Ifa$gdcw l |#}####$>$?$zddKKKd$ & F$Ifa$gdcw l $$Ifa$gdcw l kdJ$$IfT70 (z 0644 lapytcw T?$@$K$$$$ %5%n%zddKKKKK$ & F$Ifa$gdcw l $$Ifa$gdcw l kd$$IfT70 (z 0644 lapytcw T@$I$J$K$~$$$$$$$$ % %m%n%o%p%q%ξξξξξξξhcw 5CJ\aJo(hcw hq5B*aJo(phhcw hq5B*aJph#hcw hq5B*KHaJo(ph hcw hq5B*KHaJphn%o%p%q%d\KWD,`Kkd$$IfT70 (z 0644 lapytcw T$$Ifa$gdcw l 0182P. A!7"7#$%S n9_=\1rsn;II*]?@$ BaPd6DbQ8V-FcQv=HdR9$M'd]/LfS9m7Ndr}?PhT:%GO)e6OTjU8u*WVkUvVXlV;%g-eoLW0m:LMi4ApPxxBhd\. ݴZ8I^j9h9結#z";&ǠU-ju=$@h3gA# |<^Osl ہdI @P*HDA_f`0& H 8,9^l[ ̋x2;4 4d@lQfr("(8PFQ HEfk0b% A@" $ˈk.G|AZr#XbPS0$&qr)xٶTT,N* /˱|PDZD@=P&b"Z DUK@>!p!a&;Vgy{Q  YXUIVYJ"} q?!d!#DlA7(.MԂ2p w٨u9Xİ ٗIF\WXz$#8@o, (De1NSl u6mHZ p.OEQ!An$@,(?@$ BaPd6DbQ8V,i5+ZwT-8*HU.K(T + `5 B'SXY%PhT:l6t;By<"B:`ah;%gB`OMoYjs*% b !l$eB`L(EG  m |]?Q*=z* #hekf\>%ryPi9Źa@z$$K%?zs*I`tO)B,-(XPH4 D11hYt5K<ƹ5 Er`:N H<~QtW|LD=C{"0AebdP HeaHa]\p܋8! X=L@OճAfgmsrN ͂32C%**{Xʘ8FDӹLcn(:0xWSDVb93•(ZJ AҮ~G< $;AN.h5|ba< B`3 LOa g± Q@B05 B1ǖy^eh `F?(A6M kQp ca\jJ '2 0xw>G „1y+[Muhij1!~@j8^) v#~7/u_6Ĩ Pz#Pi0p,*0AEPm a89ȊN @a }猠F*ge V.~}4*#`kb19v.w)|oQ' J8zd A7e8uH0EdՕ* 1,YrBD#~C> <xA T#RjS H_ͩ71}AK 8MA@"W8zCX a$$PX Ah샄j;X녧 ~ΩZch7-(tȄ0H*CE|@h` zEYa@M T+qb "0ACrA\,c7)Җ5R y&죢ǩ&  Ul@` !{-Q7pa Rtλ:Y굧!ZixyQ^,EPZwEa3 \/a"JX6͙p?@$ BaPd6Dao0昔p6AXv8MJeRB AY T:?!L沸Qxq8!3ЪV+B&pa|PvQV;%E"_oh1`{5w@~dHB 1HW~OA2BFa].5ptU*+v<>$,`T8\.*y:U^V zvoS̬WRAE"],S3YY:|`I%Bp6yAN5mj׾H)l "Њ!b0 Ë)VU$,c д (sŊ3qx^D! ^ k. ~_ # KDL'Cd1C/`f/*$Hi&R24Q Կar.iYn Ub p;D_H$6d1XP K<ԥ\Dw"tWc8ȳ\%U"1Y0(lj{@ (Mbv۲K)TUH)\V$}4=XСB~ ABQV"(- n$j1d`hp) G&=Rދ30(P0c.ջܨ!r\ X5ZB Ke)K>NcFRS ^c0bPH.lNDZUb!]v&0$@'auXtZyg2M+y"P|b@N" &ofZ`(j `.ę$I>c$4B #!$O¿q_zT\Dp2"~8e<P-?"xBZrP&!/RVD$3`JE`K`dJ "@'t P P|Pe<_KpXO!(wqPA[`]TW' ȈS~2H(c 3b ~pjQ1F,R 8O!>H!"Xl a+aEكA:poD -dB Q(%@2i5xP4 I@a b+2qט d-b#b!:#Bf r.HC/H;pI9gAiAK+FT7F!1U ;.5 Xk(wQAD90R= 4=[y>PK@"R23a@u0IMD d~7TTx> Kix?(}F+ |NdYOhtzP]B=_QA):hq-)~31rB@Q! ~$F@D*%d3ldPz c)4F+h"!Iqz]?E% طO"Bl8pT X='B?̼BCA"м)$"JQ`+zzkZyŸ b`$FUyN@"E -$G ~0_JDfĘ:~>$eZX4np69G9::O u -0$ !v.-$%t$xB<A8!4Ih˙:@L/2sjb]zu1EE뙜3Սӯ6w9rheCG9ڰBlZ! Z;$D{9Кt',,z|ĐJK1TU((%z4C) vC∤Py QBʿR|`CȄĄ *, ±[(1MS`cdf,=i%dh086ݸH' T&y.L**caZ_n[Vì#*)`Z$`7Ršf1` )u܅BJsǒ <#˹#a4&lӝgY* ˝uecs؞(|I2\(pej \LeFoA0KA@P Ni{H&^X _Łǡ|i=soҾr1kPW pEm̹s4pgPchb] uȓqx2% d{yh!v] (  R~1@q CtmQtO3< VRiB2`  S<k"l}RS[BB5@ghWfl r<(aG ɻ{Sʁ;D 0!9' -ųG%$AѴe11R7|ql q8yc>^ !y}FB ^aʏ7`4獑l > I77]ytR }-f2I8B$&J" tvHV㜃JvX<P֡ER;b|`}L(gu(%@@?@$ BaPAUL FcQv0w;,4ǥRd]/C i~4gSY}=B$(tyl LnyQ&T7T*B Uj8eΧe|3Vk`iW   Q?cDZq} #!oӴ|p1j:%WC;7>dȿ!5n^.@@.,;Ktlׇ1R(!C8,;(5$p6XԮU*>K !?10ZAЊjx'(d$ i:z0o# ĕ%H k?d|<C-0Q% ,JP`F& }8\,7/l#Hr+5S! %܂B2`al¬S A@!Q(1IV(g)clkDY:Mj7&YXiUH&IE)HR! $Qb=GCj^Zḧ۾i[5DUo It\0 d2c՛2rH CX/ `t Q{BHNՌ-ڳQ Sw"8 X\Ev0&@(({gdaΥDǔp&K\ #k.F\&D7p [H9FQD(J(фbEvd뮶bBv%# % @n@$¨+y!ndiYv]3}q? o= "(MgBP ~arK@tP @ށC,pHdA;TfkD 5^ղQ(@DCM A!r/f>r#ʶ d@>L#[N Q~rLY+QA˜:GP ]beάb~k Ia&$ CW:Cg&A*s|lPBo!I|S>"OAY @A<2,r0F#x™\{tWj(La3 6\҈SI/U & $7C6/;ňejBCYQ]>>$y? 3@g d%P$Hɉ-07@}n!>GH r{ณDċAf*a/[H ¥d-,@}%H/B읓uGSJ5QB@^&|5T'2 JMi{uܜA'"y + Au0T9V݌1ز+p.M14$z_#5W2A5|Wk?*% @,XhMBͧh/Y#ę`-tr.˵qC$ $|zqjircf`F ׂ yaOuQ.:E"c.lpDl:E%X&HajdP_*'a{Y½ ^plI~ YVU 8"~˴)cl-=~n$v `QZV )6Q.e[r,$<+![K6M(H [ݵ{MӜ|qr\kDp\,(&C?!8kz^ ^-"ݴNIZ!p[}c.Zi"H$ԷΡҗ@2^[9Hx^IpaJ(0^hOgzOYz'p7BdL0N I?y4#xOgP~ LkDjSS Oaq'2h8C~qL 6q^zz/eqT?0BD֔=mJ%xa”R&ǣg?B$ ?=b*?@$ )x+~iDbQ8V-Ncqb BbM'JeRd\PO^/lm7Ja }?DSJH-&S(O¡Iܲԡ3> F&jta'j^oQp<$MΧ3Yp %Uy3$S0l6W^-u= tYYM s.'>aTSL)[- LP( Jsc^S³}[rs\ e H BP0~uGQ AF#G::X.+H05qj$:+ABƨA`X 2 < !tI]"Ihf1IX) vʼn`0xC_5𼂞g""XHDn! @`^DJ# 9lZ`P>/R"$;頱$]QIyIr\?}d@ul䁃 j$ S33ɢ7- H*L煵Mh:1#-h.N;Ci[߈!sVK~5`Uߪ4 1J./10M)A+đ83 pDJ!ANSydaziB Vuֺ.RtPX@["@ya,c{Na1$k11U0 񽫲2 ܅}rUn0&!b0I+ĆML",`CRR&*Fs?; 䂃b DjDOܭ%tQzRXW4y[ g8uozE$J%[&vŘRI%9p0U -VY{u mh[#y1Bha&( @ !(>)2~p,;B鹺nU)Aj6pB0>?ꈡx4H|eΌx ظ0~:ۮHHR:e cl. F+ x4QJ6t,,+-. IP.*'i{O(ާLc@daZ9`Qhфa] r([h'Q+(}EV.DZPèg"peñheg(>͞űEf@|LzB`NuѤEZ>v^%h~UہqaEV& wMd^8" zXa8N $$ $D0 2ff BY8{cETX#7fzvztj`dږ= .c߰)<A`W)YypOhY@`.łG|4<֌3Ʀ#YinYء/RwZ=_gq:ygֿH!p[hYwj1@P %ݝ"7wt>)p*`6Ʃt |^I* h8"'EOn0 2Xa:@` АQ]QiPG dT\ "@ ,[ $(eśs`.N8`^  O98C{rAC2ʠ!4X "Ce !1ȪXK$gH߫pX;a0:?@$ z=$jx_xV-FcQM'Jb"{JS9m7Ne)$}?ǤI3R)$v I"D (HdtzX%eWKep3$l1@kUgXB)4}pUX?Z+E]` EHEʥed,]M˨hVb,c蕹UZ8'#˿kzQrV* gKNje)h4qPsɸr0~n[ `H>ɻA**GaAsPS OCs#OL?ɂ`a4BAn|g9މ8 MGL H ^ H D!&9y "J @I\V L8%*$~n$v9dY SbT“,A=-1" Byr#d GB0If!\Wc@ c11LkK#U=PЕZpP \؉],xM|UIJv=p"~OqC0MGm[vdWCR@M\ QE#@ut"hS2 ɭ[$Xd2sLj-mu%6ZLOQDQ^v?=WJو&V8+tiHdX p[Ft a^`:N ɮE2fv_@4fU", #Ab pWdp^.B0 %Ip0*8+f55'$9ϙQ1x]f~d #R۞\5ƹtiN a: eu5`%BGb cp7֫"4!+T@[9d8w/@!. z:쟹`, Qh$]ABR A<c&e0d$" (BV sE@ `` 0ԛ w87am"OtA,Ȝ'!4r0, $pMRpF5:FM9 u A=H!`]apT6^4Ƙy;PWBT q" > >X T o#vq0@ΕCo+(KX_lyG84%58`pAȐ"DY!= 3^  8\%$?@$ B &%K}D" C~:6 /B4m6FNG3\@KtH$ ei|}?i@RiTJreʤAKkU4lPuR3PZT^>Eewϧm(bLkza@{Q)(Ptfh@"Dڱv5O4FL]b `HqʵcE*cr]8*Q(Q J_`4M#1˒zi4IyNS/?P`YJX.)xð% !J,Nh 3@%tJDQ! jI3ٶu:D"c)2~w!%x3`"$0'Pg;П4M"LJR3J@o7nFIb8Ƞk"pӁM F7MzL>0NM?<(MTUJ$24U!پ>a["C [ 0E[%(!v>ZŰ)k!lSaA T8\@$1y->MR<iJ!2 C#AT`H)Vuq87D5J:os\ ~d=Fbyw "@ 62bhOZ';9P .lbD H?2>ݚ,n|epA4% h-p# @Dщ#`YK-$AQ Ô9DM\/ t.aAElÑ6&%T;C=QB(HAӨ 6-xp"UE0FH1$DR,a2\AH4= d)r f8"hM3Dh3!ZP ^HA7@rڌ+hIFdəS.fx tXf_ Uatl Cf ^ `t}"±< 2~E|xDtq02RQ !:eqDҙnQڄ "|"MR1! 9 P5$qА408K.CqN@ Vk͒  $DaEi?пV[΢pVR ;ER&E]r>SŸ'dH2NxPB)VlS PGH;da iƸRH*$ ,P mmZqÍp FOFxd qWUPjC+h@"Xa=W\2 ,\ C7g A1џs(5=€Q.\ +v  NT_BtNQ!D0Pa !4O+D d-߉:dZ[L^.,oI8C$D-©4خ=)W`w~Yn 4 3e!h YQjZR V`Eę$<90A!\ yAjP_!GXѫRAHI;S\DB`C6aM#З3Vo۽lGz1) L[X"\$}MqBmM=-/Kb7*bAEy7m;v1$B R- U:V,pa,%B ?@$ BaP)dC/Hp9C ++8)rQ$NV˅0JxPC5RYAw Ɖ@WVkUּ̦WeW ;b0`0 Su;eBqʅ2W?dj1 bC4rA _Yv A$FItX yclJ$۶Db{L ĵ%RUZ k#EUpRh]/Ǖ-Vr\ڐ((J-hs9\(#al 2@$ 7b)AT4kCZffX5faJ@D COmG.!`|T2 YnR܄8z*w`%*vgZFp9H@+ YTU!i* ^c| 5Y*9dg.D*Bx@5K!MWVS9y#rяfeEc-B0"^/"1BެakHRh( *'a{ ' jFɰl %4$>D9_àaz6 hVҢ\CmDYv!H4qޘ:Gl)tx xA,JD5c/Ev@scneNjt(B*" !dƑig0)nж9)" `ttaMS @ P5tB/ I "4)q=Ǻcb Ւ; hy)”/QCtS1AJ 𭠣9G tN`F&XSaLB! 삌11TOQxsPM H,'R0CphPAVЗg bPI7ޥzلrZKYm-PUD0E!|DJ TAE1#@b eQx&=\n%|%(AI-)c q,v .S]P.'#Ĉv p(W.(TlJXA]P9>(.BhN :K 6 WA]1DFd%JlX+u=@ i]0dTɅ>Y 30poL܊ EA< 1G+yI R6ac`Qa)tMWB5Z[V}xFͫd=JI YB,x?6Bs8<08'7KPŴ:[L[Dȗ Oad,"G l0D"8pnH\PN&RCU-"(" ^67A DB鈴t& 0NИ?I0G yUZ ` |0Êl: ׉'b✓m$H N<=B ] HFZ\aj.MSoMÊN``@)V MZ F zP1gC* @~A vr|GN AAb3ъza^m\q*j!d@ &*_rFA2E n r ?@$ BaPd6@ @-X/C a0229 J[$c"(r[d2H:`WK5GAS):PЂ@ IVci*Ip2ݕ aJ 6]^QHh+E! *n7cY0|V+ ev뗃 S1 lD<  %;_8dr`W7Ai"xZ\#߂ "G WǓY,ZXv?;!fb(tJ=# B'2 A<D(#%!RSTQZȑdQBoGp^D6,L !T&X ?byg #@ЄezhB]Sh7|D _DکO zЖ&)z^ 8MD - U%IO LŁ`)  L@P@ed @u q(8 qf>5Ht_)6zw\P$q]5Qz »΃!>S.UY X`-h]Pkd*(QENj8 ;"HZ+H?o:45LR0JΖ`t =) `!Rq:ygW ϣ8yNR,5|nh}mWQ>& Qxd_Dl~^6p]ZN"UNb;)(YlZ`PquݠMEϺJ 7YXV0 %Apy_q…`0Jbf`5 [ƒae("$g`? d 3 6 %rP "25K ,PDa`[e8PP>!0Cu<˓a$Ģ\ řAb15!3r{BHtã#S PchME:@M a-畳hm|p V #p0n$،pO`o R,ElҤPXΏ|udq__qdA $[K!Y `BQyewp(2lm m\ -Q\zOy<' B8dУ4NC"' P >& AD.ZH)02PAm`Wk8VI`E_3Ȥy/ycnk^i*P ^FPS !DrZ>[ :>P-!ݐ9hPErkD4+3"h\r3aƟ' Zcg:d.ZYhS>DV f'@G2`*E赩PhM'  -f nP(e,WG^Z bȑ ` Q,%}}H@d@GIxD$dprNN]D&jSPGe<fgŬ!V IAx/`Kq`@ (@2GuČ~ A:`KFwTx+P8@T Q=|zFצQ{1 7PC?akؕ94"$""(-hJH(63_-86;sYXc6_ bZ6כcbAA_axOu >¹ }],}60k=HܹL].JrYK" V L(( MG36w XNC7+׸B {o49R|LHSH +|#W{5B,Ϗ" cA˜vc &"%-qѢe:ɉ_^r_AR )}>B N J,z ^H` *P!npv {C ?@$ BaPd6D`xATBl6Aa-A/O'~e2,uA'PQ(1OjU:VW]Y(=,Gqh[+ _w8+}TUh  䐵~ U/7WEc=TOM VC%=dR("?/~?Ʉws}pt2!BAN39u r#@8 6aOem@ P( -+G zTEP+ (€ (* 4&a9!~‹.RJ'(YhYd6MDaGsBȴRxT%ɈG&f:(P.)L~̍@@Z9sTbx}NT^t & `(B^W\)R brA %"IObDTT`- FT?>C8!lڂ ybHo؂pCDQE8d) >&Iݼg"5Ҫ(X((('-Kdqr 81bCh ͓7hJ}8s`X\ d/!* 0xgX6)G.:NVҸDzH)(I!`X dKn fL!HzFp;Uf! 7$&Ihڶ]\lięSzɟ(E(Q&Ő. br`5Jbyz^M(Bδh ߞ>#wx5*zt]hADBc> $[#J}_j|H9Fd]nr\S 9C.@D! 8-E!xb)E0`9rAa !4ň zI"Pr(em>A>'VU?lt`(B ~{ vnS@9peuKA%DHx=€Q ` M c!}>#F\` (Y*'"LybZQ"$WodIрqR!rN6eTblz]xrD$ HԨ/C|v!17q蜌~Qf2!J*R 'Qc98 v̂98q 9@#QԚ]zjs nP*@XAz>!u }'@a⦚Eм:F:L&bVNUPTh/ uTA_A(=*@D: nCQQ4= -5-$ !ǭ]\4ƹfx<(\A pX@/a(e\+!`#@ED fE&W > c0BHF`6APpP,rp™q Ha>X Mfhs&A$#{tr*N08O 4tY1.]BD SjHlJ>.IAj(A/@ܻxg \v`ii 1YEtw7lbXF/Z~I D).j<[W aU"ýD D))9L3@RR(DbW Ca $Ֆ:H bҧ3I LcP4x "DI05,#Q-&ߍ;w-NЖPڎȾ6A8V\Olɣ͠BW~ڎ;n#UZ46Ml ݜYV Z~-v켖](*D!,E#wf?l؍^[ʗ҉iH)"=ѡ8"I!$i_C-LB"PfT{Xk _q!\o(U%y܂C -oB(E̅Q pjLM / cd82w3@9H&6V6ue^ޞ }ݛj(F%V6ddW> 2 bDOc 3CI k{I"#.9 ~B:hcOH=9!݄Ff8G !᫻9Ÿ"x'o(v4 A`z Sw>/qBn h}2BHHPK(ACb B|O rYK6 D. By,*b"/VQr9kb|'!A޺*!|DBA*j Ɯx%Yb`Px5a!T!V0V -`;aFa! -21~Z P  0JOZd\V`m=(wb B M"=P"Q /d`! "C" @aN)l)CiH@4u/&3` qXխ#|'*aA 4lA>G)\EZ@  Cb4fbTQ !͒" VQ[f.!'xHL ,Ar#Px,t`1_]!0 at ₨hyb|0`NFtRaP0 0 pu4! hD**t'~o{m4 º+0ئ*f!Ę!4.a!/"R$ ?@$ BaPd6DbQ8Ve8u-~4dQhKLR("!PVR*ȌBapʅI-G$DE$%RqUi f6#<ә$K%LvK&D?nPX.BƗY-sC8;,BA!&!eRjrYϖ=e TnjCaEꠧ2W% ,P10B''=\:1+s\g$ɐIXUHfal!d؎$& ?6 aب*Y(eZeAw?n[af?cHh/ZN^e p!!aT{ +X0L99mehZ {aa#8d8p*)OBJH:N F |J{y@ x]MӡGQKDQ@e Hd-AY=IB<}""0㰃3]^Ů?ɲv""(J5 1L `m B }V_s#vT4`FU@ 0S`qq8Fm@A![l  ޜߏ>XBY R=a@%pAh2D tQ_Ȩ7G({P T >?BbqD(G8yJ܁ǸI>9 !DqEH#K ?@$ BaPd6DbQ8V-FcQv=HdR9$M'd]/LfS9m7Ndr}?PhT:%GO)e6OTjU8u*WVkUv^^^_ _(== 7'+0\8CMYs]=J|DepC  R kl`[`[$$If!vh#v9):V 706,59)ap ytcw T$$If!vh#vd #v #v#vV :V 706,5d 5 55V ap(ytcw T$$If!vh#vd #v #v#vV :V 706,5d 5 55V ap(ytcw T$$If!vh#vd #v:V 706,5d 5apytcw T$$If!vh#v9):V 706,59)ap ytcw T$$If!vh#vd #v #v#vV :V 706,5d 5 55V ap(ytcw T$$If!vh#vd #v:V 706,5d 5apytcw T$$If!vh#vd #v:V 706,5d 5apytcw T$$If!vh#vd #v:V 706,5d 5apytcw T$$If!vh#vd #v:V 706,5d 5apytcw T$$If!vh#vd #v:V 706,5d 5apytcw T$$If!vh#vd #v:V 706,5d 5apytcw T$$If!vh#v9):V 706,59)ap ytcw T$$If!vh#vz #v:V 706,5z 5apytcw T$$If!vh#vz #v:V 706,5z 5apytcw T$$If!vh#vz #v:V 706,5z 5apytcw T$$If!vh#vz #v:V 706,5z 5apytcw T$$If!vh#vz #v:V 706,5z 5apytcw T$$If!vh#vz #v:V 706,5z 5apytcw T$$If!vh#vz #v:V 706,5z 5apytcw T$$If!vh#vz #v:V 706,5z 5apytcw T$$If!vh#vz #v:V 706,5z 5apytcw T$$If!vh#vz #v:V 706,5z 5apytcw T$$If!vh#vz #v:V 706,5z 5apytcw T$$If!vh#vz #v:V 706,5z 5apytcw Tb e66666668&6FVfv6888&6FVfv&6FVfv&6FVfv&6FVfv&6FVfv&6FVfv8XV~PJ_HmH nHsH tHJ`J cke $1$a$ CJKH_HaJmH nHsH tH$A`$ ؞k=W[SONi@N nfh*B*phPK![Content_Types].xmlN0EH-J@%ǎǢ|ș$زULTB l,3;rØJB+$G]7O٭V[ZTV"Lc8Wcǟ^|௷2P+|&Zq6hr*;L}Z<İTUoi^K71`oa_utho0WZ՚6sCA5եUyZor2h4!cC1wp4kx˹% I_D 1o|yrxûw|o9pw?F?{~33~{_|s!ЈHt]c&*d(^m Ĵc#$R"B}eYǎ6q#x]}/Nn:C1QD0rۜ6Quf3sm*qsDHehKPK! ѐ'theme/theme/_rels/themeManager.xml.relsM 0wooӺ&݈Э5 6?$Q ,.aic21h:qm@RN;d`o7gK(M&$R(.1r'JЊT8V"AȻHu}|$b{P8g/]QAsم(#L[PK-![Content_Types].xmlPK-!֧6 0_rels/.relsPK-!kytheme/theme/themeManager.xmlPK-!@theme/theme/theme1.xmlPK-! ѐ' theme/theme/_rels/themeManager.xml.relsPK] qt| 5@$q%"',18$ J `  l .`\@Wa+k o!!|#?$n%q% !#$%&()*+-./023456794YiqXl,b$=\1rsn;A_2t@(  ~  :A(8?? VGr 1#" ?B S  ?q T#+s~ U _ !fjV_ss3Mw.M  \ u @BMMW)N,6h(mw  (}@Ks|]m ]P|81'r6T@7u^=_0A@fH@ncFL8j?H"N\9l{ PKxvLLmg3;;5rL@\^`\OJQJo(hHH\^H`\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHl4\^4`\OJQJo(hHn \^ `\OJQJo(hHu| \^| `\OJQJo(hHl \^ `\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHH\^H`\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHl4\^4`\OJQJo(hHn \^ `\OJQJo(hHu| \^| `\OJQJo(hHl \^ `\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHH\^H`\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHl4\^4`\OJQJo(hHn \^ `\OJQJo(hHu| \^| `\OJQJo(hHl \^ `\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHH\^H`\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHl4\^4`\OJQJo(hHn \^ `\OJQJo(hHu| \^| `\OJQJo(hHl \^ `\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHH\^H`\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHl4\^4`\OJQJo(hHn \^ `\OJQJo(hHu| \^| `\OJQJo(hHl \^ `\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHH\^H`\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHl4\^4`\OJQJo(hHn \^ `\OJQJo(hHu| \^| `\OJQJo(hHl \^ `\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHH\^H`\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHl4\^4`\OJQJo(hHn \^ `\OJQJo(hHu| \^| `\OJQJo(hHl \^ `\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHH\^H`\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHl4\^4`\OJQJo(hHn \^ `\OJQJo(hHu| \^| `\OJQJo(hHl \^ `\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHH\^H`\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHl4\^4`\OJQJo(hHn \^ `\OJQJo(hHu| \^| `\OJQJo(hHl \^ `\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHH\^H`\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHl4\^4`\OJQJo(hHn \^ `\OJQJo(hHu| \^| `\OJQJo(hHl \^ `\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHH\^H`\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHl4\^4`\OJQJo(hHn \^ `\OJQJo(hHu| \^| `\OJQJo(hHl \^ `\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHH\^H`\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHl4\^4`\OJQJo(hHn \^ `\OJQJo(hHu| \^| `\OJQJo(hHl \^ `\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHH\^H`\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHl4\^4`\OJQJo(hHn \^ `\OJQJo(hHu| \^| `\OJQJo(hHl \^ `\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHH\^H`\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHl4\^4`\OJQJo(hHn \^ `\OJQJo(hHu| \^| `\OJQJo(hHl \^ `\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHH\^H`\OJQJo(hHn\^`\OJQJo(hHu\^`\OJQJo(hHl4\^4`\OJQJo(hHn \^ `\OJQJo(hHu| \^| `\OJQJo(hHl \^ `\OJQJo(hHn\^`\OJQJo(hHuH@T@7u^=_0A@m P|8cF"N'r6vLLm?H;;5r                                                                                                                                       jU%+l#,/ '?H@jb- [ cw 6W#i-1/_=IAC$jL QimQ%qY)[Iaeh &kfqjt+upal2Za5 ]s{[N> \P&EnqOW&)[e5k79eiqs commondata<eyJoZGlkIjoiYmJjMTQ4YTZjOTMyMzVlZWQyMWY2NjFmNWFiNGMxNTkifQ==@ eeee@{q@UnknownG*Ax Times New Roman5Symbol3. *Cx Arial[ |8I{~ LightArial Unicode MS-= |8wiSO;([SOSimSun;WingdingsA BCambria Math AQhU3$ >33>33!72cc KQP) ?22!xx IBMY~gH          Oh+'0P    $08@HIBMNormal9Microsoft Office Word@"@:@׏*>3՜.+,D՜.+, X`t|  ߷˾3c 00ow _PID_HLINKSKSOProductBuildVerICVAh~Xmailto:24678790@qq.com2052-11.8.2.11019$EB73ED8ADDBF403F9EFA731D86CDC207  !"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghiklmnopqrtuvwxyz{|}~Root Entry Fn*Data j31TablesKWordDocumentsSummaryInformation(DocumentSummaryInformation8CompObjn  FMicrosoft Word 97-2003 ĵ MSWordDocWord.Document.89q