Скачать презентацию Programming Neural Networks and Fuzzy Systems in FOREX Скачать презентацию Programming Neural Networks and Fuzzy Systems in FOREX

7cf367fc756e646d2d0eeac8b1c1f30a.ppt

  • Количество слайдов: 24

Programming Neural Networks and Fuzzy Systems in FOREX Trading Presentation 0 Balázs Kovács (Terminator Programming Neural Networks and Fuzzy Systems in FOREX Trading Presentation 0 Balázs Kovács (Terminator 2), Ph. D Student Faculty of Economics, University of Pécs E-mail: kovacs. balazs. ktk@gmail. com Dr. Gabor Pauler, Associate Professor Department of Information Technology Faculty of Science, University of Pécs E-mail: pauler@t-online. hu

Content of the Presentation Basic course info Purpose of the Course Agenda Accessibility of Content of the Presentation Basic course info Purpose of the Course Agenda Accessibility of course materials FOREX Trading Bot Building Contest Requirements, Grading and Consultation Introduction Basic terms of Stock Market/FOREX Fractal Theory of Stock/Currency Pair Prices Basic terms of Distribution Free Estimators (DFE) Basic terms of Rule-Based Systems (RBS) Basic terms of Learning Algorithms (LA) Basic terms of Artificial Neural Networks (ANN) Biologic analogy: Neurons in Human brain Comparison with silicon-based hardware Biologic Neuron and its Mathematical Model Neural references

Basic course info: Purpose of the Course Nowadays there are wide range of fancy Basic course info: Purpose of the Course Nowadays there are wide range of fancy FOREX „course providers” which promise that you can be a millionaire within 4 weeks, without any serious economic and mathematic training, just completing 1 week rapid course where you learn drawing curves to charts visually. By contrast, we do not teach how you can be rapidly millionaire with FOREX. Instead of it we teach how to avoid loosing everything you have very rapidly with FOREX: Participants will be trained besides basics of FOREX and how to use Meta Trader 4 (MT 4) FOREX Platform: Recognizing their psychologic limits and assembling customized trading strategies accordingly, The MQL programming language of MT 4 to create your own indicators, Theoretical basics of Artificial Neural Networks and Fuzzy Systems, Using the Joone open-source Neural Shell under GNU license, programming it in Java and set up its data link with MT 4. To motivate gifted students, we organize a FOREX Trading Bot Contest paralel with our course, where team 3 -4 students can tune their software to reach maximum amount of return from limited amount of investment, within limited time frame making limited number of trades As a unique option Trading Bots with extremely high computational requirement can be run at the new University of Pecs Supercomputer in C++ environment The course has English language course material, even if it presented in Hungarian: To close out simple-minded Gamblers (Szerencsejátékos) Because – even if you have trade platforms and courses in Hungarian - almost every additional resource in FOREX you really need (eg. indicator source codes, economic analysises, user guides of trading bots) are most freshly available only in English! So the main outcome of this course is not being a millionaire in 4 weeks (which is unrealistic at FOREX anyway) but to develope proficiency using Artificial Neural Networks and Fuzzy Systems in a difficult simulated battleground called FOREX. And that knowledge can result getting better paid positions in many areas of engineeering or business

Basic course info: Course Agenda Legenda: Week 0 1 2 3 4 5 6 Basic course info: Course Agenda Legenda: Week 0 1 2 3 4 5 6 7 8 9 10 11 12 Presented by Dr. Gabor Pauler Presented by Balázs Kovács Presentation Quiz Grade% Practice Home assignment Grade% Introduction, grading, Install MT 4, create - Forex basics 1 3% Neural basics 1 account Neural basics 2, Learning methods: Neural 3% MT 4 GUI Basic trade in MT 4 3% Hebb, Delta, basics 1 Backpropagation 1 Learning Backpropagation 2 3% Basic indicators Use of indicators 3% methods Backpropaga Indicator programming in Joone GUI 3% MQL programming 3% tion MQL Time series forecasting networks and their Compound indicators in Joone GUI 3% Compound indicators 3% representation in MT 4 Joone Trading strategies in Time series Connecting MT 4 with MT 4 -Joone 3% 3% MT 4 nets Joone connection Rule based systems: Trading 3% CRT in SPSS 3% Crisp inference CRT strategy Rule based systems: Fuzzy inference, multi CRT 3% Stock Futures 3% Fuzzy basics valued results Fuzzy. Tech 1 Fuzzy basics 3% Fuzzy. Tech 2 Breasts 3% Special topologies: RBF, Fuzzy. Tech 3% Topology diagrams Character design 3% ART, Kohonen Spec Neurofuzzy, FAM 3% FAM in Fuzzy. Tech FAM 3% topology Text mining basics FAM 3% Text mining in SPSS Text mining 3% Text mining topologies Text mining 3% Text mining in Joone -

Basic course info: Accessibility of course materials All course materials are available at PTE-TTK Basic course info: Accessibility of course materials All course materials are available at PTE-TTK Szentágothai Szakkollégium website: ftp: //szentagothai. ttk. pte. hu/pub/pauler/Forex/ in form of Power. Point presentations and practices These are NOT conventional „three sentences/slide” projectable presentations, but almost full-text materials with: Linked-in case study materials Step-by step animated software usage usable at computer lab However it is highly recommended for students to print them out in handout format and taking notes to slides, as questions in quiz may be represented from oral comments of tutor also We can’t use TAB here! All course materials are in English to capture Business English But presentations are in Hungarian, and we have Hungarian Notes MT 4 GUI can be both

Basic course info: FOREX Trading Bot Building Contest To motivate gifted students, we organize Basic course info: FOREX Trading Bot Building Contest To motivate gifted students, we organize a FOREX Trading Bot Contest paralel with our course, where team 3 -4 students can tune their software to reach. Rules of the contest are: Server: Fx. Pro MT 4 Base currency: USD Maximum Leverage: 1: 50 Demo account capital: 5000 USD http: //usd. kurs 24. com/huf/? q=5000 Platform: Fx. Pro MT 4 Client Terminal http: //www. fxpro. com/hu/downloads/platforms/client-terminal Operating system of trading bot: Windows 2000, XP, Vista, Windows 7 Time range: 2011. 10. 8: 00: 01 - 2011. 12. 08. 7: 59 Trading hours: whenever markets are open Currency pairs: all possible pairs of EUR, USD, GBP, CHF, JPY, CAD, AUD, NZD can be traded in demo account Who can participate: registered students of current course Performance benchmarks: Passively managed static currency portfolio, Tutors demo account Maximal number of modifications on a trading bot: 5 Minimal number of trades completed by bot: 10 (without closing) Using any foreign code in bots without referencing it will result in immedaiate exclusion from contest Opened positions will be closed at the end of time range by tutors Winner team will be the one with the highest balance at the closing Identical balances among more teams will result in deuce Relative result% = Team balance/Tutor benchmark balance of teams

Basic course info: Requirements, Grading and Consultation Mid-semester requirements: Max. 10 × 3 points Basic course info: Requirements, Grading and Consultation Mid-semester requirements: Max. 10 × 3 points = 30 points from simple 5 -question quizes written at the beginning of presentations where students are evaluated individually Quizes are from the last presentation and practice Missed quizes can be substituted by one extra 6 point quiz ad the end of semester Max. 10 × 3 points = 30 points from home assignments evaluated at project team-level. Teams are free to reallocate their home assignment points internally to proportionate it to contribution of their members! Home assignments are due to the beginning of next practice Missed home assignments cannot be replaced after deadline as they are group assignments Max 40 team points from trading bot contest = 40 × Relative result% Grading of individual students: 0 -29 points: Reject signing course(0), 30 -49 points: Fail(1), 50 -59 points: Sufficit(2), 60 -69 points: Medium(3), 70 -79 points: Good(4), 80 -points: Excellent(5) In case of Fail(1), there are 2 possibilities for correction at oral exam from course material of presentations to get credit Consultations: Tutors will provide consultation at Department of Informatics, PTE-TTK, at times prearranged at pauler@t-online. hu or kovacs. balazs. ktk@gmail. com Results: Students can track their mid-semester results at ftp: //szentagothai. ttk. pte. hu/pub/pauler/Forex/Exam. Forex/

Content of the Presentation Basic course info Purpose of the Course Agenda Accessibility of Content of the Presentation Basic course info Purpose of the Course Agenda Accessibility of course materials FOREX Trading Bot Building Contest Requirements, Grading and Consultation Introduction Basic terms of Stock Market/FOREX Fractal Theory of Stock/Currency Pair Prices Basic terms of Distribution Free Estimators (DFE) Basic terms of Rule-Based Systems (RBS) Basic terms of Learning Algorithms (LA) Basic terms of Artificial Neural Networks (ANN) Biologic analogy: Neurons in Human brain Comparison with silicon-based hardware Biologic Neuron and its Mathematical Model Neural references

Basic terms of Stock Market/FOREX 1 The Stock Exchange (részvénytőzsde) is a Non-profit Company Basic terms of Stock Market/FOREX 1 The Stock Exchange (részvénytőzsde) is a Non-profit Company (non-profit társaság ), what is Exclusive (Kizárólagos) trading place of stocks of Publicly Quoted (tőzsdére bevezetett, nyílvánosan árfolyam-jegyzett) Companies (részvénytársaságok). These are larger, stabile firms complying strict Accounting (Számviteli) rules. Stocks of smaller companies not quoted publicly are traded at Over The Counter (OTC) market. Macroeconomic (Makrogazdasági) function of stock exchange is Effective Allocation of Investment Resources (hatékonyan ossza el a vállalkozások közt a beruházási erőforrásokat) allocating more money to more profitable companies with larger growth in a public, open competition. Microoeconomic (Mikrogazdasági, vállalati szintű) functions of Stocks/Equity (Rész-vénytőke): It helps Raise Funds (Tőkét gyűjt) necessary for operating a company and: Represents proportional Ownership/share (tulajdonrésze) in a company, giving the right to Vote (Szavaz) in Board of Directors (igazgatótanács) governing it, except: non-voting stocks Profitable companies pay Dividend (osztalék) of profit for that, but it is not guaranteed, except: if it is Preferred Stock (elsőbbségi/aranyrészvény): always pays dividend, but cannot be sold and usually does not have vote Ordinary stocks can be Sold (eladható) on the stock exchange any time at Spot Stock Price (aktuális árfolyam), or at Futures (határidős árfolyam) except: if the company has Pre-emptive Option (elővételi jog), to block Hostile Takeover (támadó célú részvényfelvásárlás) by competitor firms If we Bought (vettük) or Underwrite (Lejegyeztük) a stock in the past, and there was Hausse, Bull (árfolyamemelkedés) we can earn Yield (árfolyamnyereség). If there was Baisse, Bear (csökkenés) then we Loose (veszt).

Basic terms of Stock Market/FOREX 2 Equity is the most profitable but most risky Basic terms of Stock Market/FOREX 2 Equity is the most profitable but most risky tool of Investment Portfolio Management (Tőke befektetési portfolió menedzsment): You can buy and hold (Long) stocks of profitable and less risky companies (Blue Chips) to make profit from dividend or price increase, and liquidate stocks (Short) of bad companies to avoid loss. It can use 3 basic techniques: Hedge (Fedezeti ügylet): to short/long a stock whose price tendencyously moves against a price of another stock or Currency (Valuta) longed/shorted to eliminate risk of loss from adverse price movement. Less risky, less profitable. Arbitrage (Arbitrázs): short/long a stock very rapidly (1 day-some hours) to make profit from minor price fluctuations. Medium risk, medium profitable. Speculation (Spekuláció): open a short/long Position (Pozíció) for longer time frame against the price Expectations (Várakozás) of the whole market, and try to influence them with tricks to rapidly change their expectations. Very risky, very profitable. Actors of stock exchange: Broker (bróker): does not own stock just trades it by Comission (Megbízás) of the owner for a Fee (Díj), Dealer (díler): can own stocks Underwriter (undervrájter): can buy all stocks of a new company for re-sale. From broker to underwriter they have more rights to perform difficult and risky trades, but they have to comply more and more strict accounting and stock exchange rules FOREX, FOReign EXchange (Devizatőzsde) differs from ordinary stock exchange 2 ways: Instead of trading stocks against one Currency (Valuta) eg. (Sell IBM for USD), several Foreign Exchanges (Deviza, valutára szóló számlakövetelés) are traded against each other in Currency Pairs (Valutapárok): eg. USD EUR, GBP CHF, JPY EUR, etc. There are only brokers called FOREX companies/providers trading with someone else’s money, who want to hedge, arbitrage or speculate

Fractal Theory of Stock/Currency Pair Prices Both at Stock Exchange/FOREX there is strong Information Fractal Theory of Stock/Currency Pair Prices Both at Stock Exchange/FOREX there is strong Information Asimmetry (Információ aszimmetria): most investors do not have any direct information about: Changing technology level and marketing efficiency of a company (denoted with green) Plans of Governments (Kormány) and Central Banks (Központi Bank) of 2 countries determining at most price of a given stock/currency pair long term They have to decide allocation of their money among stocks/currencies from partial information and their expectations, so they tend to fall in selling/buying panic at sudden big changes. Therefore, both Stock Exchange/FOREX are strictly controlled markets with many safety rules. But this will result in a Stepped (Lépcsős) price (denoted with red) update behavior: Without strong external impulse brokers tend to build „dream worlds” setting up prices by their expectations ignoring slow and small changes of reality (eg. In „. com boom” of 2000 s, small internet-based companies were worth more than General Electric and other industrial giants) But when the difference between them gets to big, they update price in smaller-bigger sudden steps, instead of continous change As prices are influenced by many different lenght cycles (eg. 1 year: seasons. . 1 day: daily close), sudden steps are Embedded (Beágyaz) into each other at several levels, it creates Fractal (Fraktál)-type structures: price steps in time have self-similar details embedded into each other It makes Price Forecasting (Árelőrejelzés) necessary for trading extremely difficult Function Estimation (Függvény becslési) problem: Prices of stocks/currency pairs are 400$ influenced by numerous parameters creating complex multivariate (Sokváltozós) functions Price data is very Noisy (Zajos) dis- 300$ torted by random disturbances, so Stochastic (Sztochasztikus) function estimation is necessary from a Sample (Minta) of prices 200$ Sometimes it is hard to assemble any function from future price expectations collected from different information sources: spot price( ) can adapt to 100$ reality in more alternative fractal path 12 16 8 24 20 4 Week

Basic terms of Distribution Free Estimatiors (DFE) Distribution Free Estimators (Eloszlásfüggetlen becslési y rendszer) Basic terms of Distribution Free Estimatiors (DFE) Distribution Free Estimators (Eloszlásfüggetlen becslési y rendszer) can estimate output of a complex, multivariate function from inputs. Functional transformation is estimated from previously observed (Megfigyelt) Sample (Minta) of noisy input-output values, and it does not make any assumptions on Probability Distribution (Valószínűségi Eloszlás) of sample. It means that the function can be reasonably complex. There are Analytic (Függvénytani) methods of Approximating (Közelít) complex functions: Taylor Series (Taylor-sor): it approximates a nonlinear function (Eg. Sin(x)) with a suitably parametered higher order polynom in a given range Fourier Transform (Fourier-transzformáció): a A complex nonlinar function (eg. Stock price, sound wave, etc. ) is assembled as weighted sum of Sin(x) type functions with different wavelenght and phase. Evaluation of analytic methods: They have relatively low Computational requirement (Számolásigény) They require high level analytic mathematical knowledge They are not Modular (Moduláris): modeling any additional local „bumps” or „steps” will result exponentially more complex global formulation Therefore, we will not deal with analytic approximation methods in this course. Instead of them, we will use Rule Based Systems, RBS (Szabályalapú rendszerek) x t

Basic terms of Rule-Based Systems (RBS) 1 Rule-Based Distribution Free Estimators (szabály- y alapú Basic terms of Rule-Based Systems (RBS) 1 Rule-Based Distribution Free Estimators (szabály- y alapú eloszlásfüggetlen becslési rendszerek) approximate Control Function (Vezérlési függvény) ( ∕ ) among Input-Output Variables (I/O változók) of Decision Space (Döntési tér) with the help of Rule v Basis (Szabálybázis) containing k=1. . l finite set of ju IF rk Rules(Szabály): They Associate (Egymáshoz rendel) vi, vj x [vil, viu] values, or [vil, viu] intervals of xi i=1. . n input THEN and yo o=1. . O output variables They have Linguistic(Nyelvi) representation: IF y [vjl, vju] Input. Var 1 = Intreval AND Input. Var 2 = Interval AND. . THEN Output. Var = Interval vjl They have Graphic (Grafikus) representation: v viu multi-dimensional Hyperbars (Hipertéglatest) in il x 2 decision space (we denote them Yellow █) Rules of a rule basis can be Mutually Exclusive y (kölcsönösen egymást kizáróak): they have no Intersection (Metszet) = Common subset (Közös részhalmaz) in decision space. Alternatively, they can be Overlapping (Átlapolóak) All rules of the basis has mx(rk) Validity (érvényesmx(rk) = 1 ségi) value, which shows whether the rule is Valid/ Fires (Tüzel) (Red █) at a given x vector (Green O) of input variables: x rk If there is only one rule in the base to fire at any x input vector then rule x basis is Non-Contradictive (Ellentmondásmentes), x 1 else Contradictive (Önel-lentmondó) x

Basic terms of Rule-Based Systems (RBS) 2 Effective approximation of continous functions would y Basic terms of Rule-Based Systems (RBS) 2 Effective approximation of continous functions would y P(x rk)= require large number of rules in the base to get rea. P(x rk)= 0. 025 mx(rk) sonable Resolution (Felbontás), eating up resources 0. 025 To avoid this, rules can have wk [0, 1] importance weights. Estimated otput yx* is computed as weighted sum of output values of firing rules. This is called mx(rk) P(x rk)= Interpolation (Interpoláció) among rules: yx* = Sk wk × mx(rk) × yk (0. 1) 0. 945 P(x rk)= Interpolation enables to model continous control func 0. 945 mx(rk) tions with less rules more effectively. It has 2 methods: Bayesian Probability (Bayes-i valószínűség) rules: It uses mutually exclusive, Crisp (Éles) rule base mx(rk) Where multiple rules can fire binary mx(rk) {0, 1} for a P(x rk)= given x input vector P(x rk)= mx(rk) 0. 020 But simutaneous firing rules Occour (Bekövetkez) 0. 020 only with a pk [0, 1] Probability weight (Valószínűségi súly), where sum of their probabilities x 1 x 2 is 1 creating Probability distribution (Valószínűségeloszlás): Sk pk × mx(rk) = 1 (0. 2) It is supported by Probability theory (Elmélet) y P(x rk)= 0. 020 It requires data about probabilities of relatively large number of mutually exclusive rules, which is unrealistic to get in the practice P(x rk)= 0. 025 mx(rk) Fuzzy Rule Inference (Fuzzy szabály következtetés): P(x rk)= 0. 945 mx(rk) Rule basis has overlapping rules: Boundary (Határ) of Support (Tartó) of one rule are in the middle of support of neighboured rules y* mx(rk) [0, 1] validity of a rule can change continously: P(x rk)= 0. 945 mx(rk) It is 1 in the middle of support and 0 at boundary (we P(x rk)= 0. 020 denote it with yellow shading), forming not crisp/fuzzy rules: they occour certainly but their P(x rk)= 0. 020 validity is uncertain/changing gradually mx(rk) wk weights do not form probability distribution x Theoretically it is less sound method But can model complex nonlinear continous x 1

Basic terms of Learning Algorithms (LA) 0. 80 Profit/ Manual definition of several thousand Basic terms of Learning Algorithms (LA) 0. 80 Profit/ Manual definition of several thousand rules and their Assets 0. 18 weights with the help of experts is expensive, slow Liabilities/ Thats why Expert System Shells, ESS (Szakértői 0. 14 0 $ 0. 1 rendszer shell) - using manual Bayesian probabilistic Assets $ $ rule bases - failed to become the mainstream of Artificial Intelligence, AI (Mesterséges Intelligencia) $ $ $ So we need Learning Algorithms(Tanuló Algoritmus) $ $ which can set up rules and their weights automati-cally $ $ form an X, Y Sample database (Minta adat-bázis) of pre$ $ viously Observed (Megfigyelt) j=1. . m xj , yj vectors of xi $ $$ $ $ i=1. . n input/yo o=1. . O output vars. They have 2 groups: $ $ $$ $$ Classification and Regression Trees, CRT $ $ (Klasszifikációs és regressziós fák) algorithms: $ $ $$$ $ They can estimate only discrete valued (Diszkrét $ $ $$ $ értékű) output variables from continous/discrete $ $ $$ $ $ $ $$ inputs (Eg. Estimate Bankrupcy/Survival of a 0. 10 $ company from its financial rates) $ $ $ 0. 13 Building Decision tree (Döntési fa) of connected 0. 16 Cash. Flow/ crisp Bayesian probability rules Liabilities Trying to set up rule boundary values at each input variable, which separate best output values Low computational reqirement Can use only crisp hyperbar rules, which are ineffective modelling complex nonlinear Transversal (Átlós) control functions Artificial Neural Networks, ANN (Mesterséges Neurális Hálózatok): they can estimate continous/discrete outputs from continous/discrete inputs Building kind of „implicte fuzzy rules”, without liguistic represntation and direct acces by user From random initial boundaries and rule weights They can model complex nonlinear, transversal control functions (Eg. Recognizing a letter „N” from dots of ink scanned in a picture) effectively At a price of difficult parametering and brutally high 0. 69 0. 30

Content of the Presentation Basic course info Purpose of the Course Agenda Accessibility of Content of the Presentation Basic course info Purpose of the Course Agenda Accessibility of course materials FOREX Trading Bot Building Contest Requirements, Grading and Consultation Introduction Basic terms of Stock Market/FOREX Fractal Theory of Stock/Currency Pair Prices Basic terms of Distribution Free Estimators (DFE) Basic terms of Rule-Based Systems (RBS) Basic terms of Learning Algorithms (LA) Basic terms of Artificial Neural Networks (ANN) Biologic analogy: Neurons in Human brain Comparison with silicon-based hardware Biologic Neuron and its Mathematical Model Neural references

Neurons in Biology Human brain contains 1011 Neurons (Idegsejt) connected with 1016 Synapses (Szinapszis) Neurons in Biology Human brain contains 1011 Neurons (Idegsejt) connected with 1016 Synapses (Szinapszis) organized in Hemispheres (Félteke) > Cortexes (Kéreg) > Layers (Mező) > Blocks Unisolated short Dendrits(Ág) transmit incoming electric signals at 2. 3 m/s to Cell membrane(Sejtfal)of neuron collecting electric charge At certain m. V potential Treshold (Határérték), neuron emits electric signal by its Signal function (Jelzési függvény), which is tranmitted at 90 m/s on long synapses covered with isolator Myelin (Mielin) jumping over the Ranvier-gaps (Rés) Excited Sytaptic terminals (Végbunkó) emit Neurotransmitter(Ingerü -letátvivő) molecules (Eg. Acetilcolin, Opiats) Opening ion channels on other neurons membrane making them ac-

Comparison of Neuron with Silicon-based Hardware wik Si(xit) ui li wji wik bi ai Comparison of Neuron with Silicon-based Hardware wik Si(xit) ui li wji wik bi ai Sj xit wji In the electron microscope image above we can see a neuron laid on leads of a modern microchip. Neuron is 10 -12 times bigger than condensers and transistors of basic logic gates, however it can perform such a nonlinear computing function, which requires hundreeds of basic logic gates in a math cooprocessor. Moreover, neurons require much less energy and produce much less heat than silicon-based chips. Currently a 100 TByte blade-supercomputer comparable in storage capacity with human brain - but still inferior in speed, as brain can share work among 1011 simple processors instead of 103 more difficult ones - consumes 2 -3 m 3 space, 380 V industrial current and cooling capacity of a supermarket Human brain consumes 1500 cm 3 volume even storing oxygene and glucose for 15 -20 secs of work, and requires 5 -10 Watts of power input and cooling

Biologic Neuron and its Mathematical Model Fuctions of a neuron in ANN Mathematical Model: Biologic Neuron and its Mathematical Model Fuctions of a neuron in ANN Mathematical Model: Non-volatile Memory (Permanens memória): ji synapses connecting j=1. . m neurons with i=1. . n neurons in the network during t=0. . T time periods transmit sjt R signals of jth neuron in tth period with changing wjit Intensity/ Weight(Súly). Teaching/ Training(Tanítás) of net means changing the initially random wji 0 R weights. All information learnt is stored as synaptic weights Volatile Memory (Rövid távú memória): a neuron aggregates wjit×sjt weighted signals of incoming synapses into a xit Membrane value (Membrán érték) in the Activation Process (aktivációs folyamat), additionally they Passively decay (Passzív lecsengés) membran value by (1 -di) Decay Rate (Lecsengési ráta) to keep membrane value within [li, ui] Lower/Upper bounds (Alsó/Felső Korlát) and smooth (Simít) its changes in time. There are 2 methods of membrane value aggregation: Additive (Additív): xit=di(Sj(wjit×sjt)/Sj(wjit))+ +(1 -di)×xit-1 i=1. . n, j=1. . m, t=1. . T (0. 3) Multiplicative (Multiplikatív): xit=di. Pj(sjtwjit)(1/ Sj(wjit))+ +(1 -di)×xit-1, i=1. . n, j=1. . m, t=1. . T (0. 4) Aggregated membran value emits signal by monotonic increasing (Monoton növekvő) signal function with ai inflexion point as signal treshold and bi slope: sit = 1/ (1+e-bi×(xit-ai)), i=1. . n, t=1. . T (0. 5) wik bi Si(xit) ui li wji ai Sj xit wji

Content of the Presentation Basic course info Purpose of the Course Agenda Accessibility of Content of the Presentation Basic course info Purpose of the Course Agenda Accessibility of course materials FOREX Trading Bot Building Contest Requirements, Grading and Consultation Introduction Basic terms of Stock Market/FOREX Fractal Theory of Stock/Currency Pair Prices Basic terms of Distribution Free Estimators (DFE) Basic terms of Rule-Based Systems (RBS) Basic terms of Learning Algorithms (LA) Basic terms of Artificial Neural Networks (ANN) Biologic analogy: Neurons in Human brain Comparison with silicon-based hardware Biologic Neuron and its Mathematical Model Neural references

References 1 Hungarian language course notes: Notes Neural networks biologic analogy: http: //health. howstuffworks. References 1 Hungarian language course notes: Notes Neural networks biologic analogy: http: //health. howstuffworks. com/brain. htm Neural networks chatroom: http: //www. geocities. com/siliconvalley/lakes/6007/Neural. htm GNU-licensed neural software: Source code libraries in C++, without install utility: SNNS: http: //www-ra. informatik. uni-tuebingen. de/SNNS/ (+install and user guide) http: //www. generation 5. org/xornet. shtml http: //www. netwood. net/~edwin/Matrix/ http: //www. netwood. net/~edwin/svmt/ http: //www. geocities. com/Athens/Agora/7256/c-plus-p. html http: //www. cs. cmu. edu/afs/cs. cmu. edu/user/mitchell/ftp/faces. html http: //www. cog. brown. edu/~rodrigo/neural_nets_library. html http: //www. agt. net/public/bmarshal/aiparts. htm http: //www. geocities. com/Cape. Canaveral/1624/ http: //www. neuroquest. com/ http: //www. grobe. org/LANE http: //www. neuro-fuzzy. de/ http: //www. cs. cmu. edu/afs/cs/project/airepository/ai/areas/neural/systems/cascor/ http: //www. cs. cmu. edu/afs/cs/project/airepository/ai/areas/neural/systems/qprop/ http: //www. cs. cmu. edu/afs/cs/project/airepository/ai/areas/neural/systems/rcc/

References 2 GNU-licensed neural software: Source code libraries in Java: Java Neural Networks by References 2 GNU-licensed neural software: Source code libraries in Java: Java Neural Networks by Jochen Frölich: http: //fbim. fhregensburg. de/~saj 39122/jfroehl/diplom/e-index. html (Java Class, Internet applet about Kohonen-nets, free, no GUI, Tutorial in HTML) http: //www. philbrierley. com/code http: //rfhs 8012. fh-regensburg. de/~saj 39122/jfroehl/diplom/e-index. html http: //neuron. eng. wayne. edu/software. html http: //www. aist. go. jp/NIBH/~b 0616/Lab/Links. html http: //www. aist. go. jp/NIBH/~b 0616/Lab/BSOM 1/ http: //www. neuroinformatik. ruhr-uni-bochum. de/ini/PEOPLE/loos http: //www. neuroinformatik. ruhr-unibochum. de/ini/VDM/research/gsn/Demo. GNG/GNG. html http: //www. isbiel. ch/I/Projects/janet/index. html http: //www. born-again. demon. nl/software. html http: //www. patol. com/java/NN/index. html http: //www-isis. ecs. soton. ac. uk/computing/neural/laboratory. html http: //www. neuro-fuzzy. de/ http: //openai. sourceforge. net/ http: //www. geocities. com/aydingurel/neural/ http: //www-eco. enst-bretagne. fr/~phan/emergence/complexe/neuron/mlp. html Biologic modelling software: Neuron: http: //www. neuron. yale. edu/neuron/ (free, GUI, Win XP install, Tutorial in HTML) Genesis: http: //www. genesis-sim. org/GENESIS/ (free, GUI, Win XP install, Tutorial in HTML) PDP++: http: //www. cnbc. cmu. edu/Resources/PDP++//PDP++. html (C++ source code library, GUI, Win XP install, Tutorial in HTML)

References 3 Decision support software: JNNS: http: //www-ra. informatik. uni-tuebingen. de/software/Java. NNS (Simplified SNNS References 3 Decision support software: JNNS: http: //www-ra. informatik. uni-tuebingen. de/software/Java. NNS (Simplified SNNS in Java, GUI, Win XP install, Tutorial in PDF) JOONE: http: //www. joone. org (Java, GUI, Win XP install, Tutorial in PDF) Commercial neural decision support software: Neuro. Solutions: http: //www. neurosolutions. com/download. html (60 days shareware, no save, GUI, Win XP install, Excel Add-in, Excel Wizard, MATLAB modul, Tutorial in PDF Medical, automotive appliacations) Neur. OK: http: //soft. neurok. com/dm/download. shtml (Excel Add-in, C forráskód, XML-es felület, Win XP install, financial applications) Easy. NN: http: //www. easynn. com/dlennp. htm (30 days shareware, GUI, Win XP install, Tutorial in HTML, financial forecasting applications) ALNFit Pro: http: //www. dendronic. com/downloadalnfit_pro. shtml (30 days shareware, GUI, Win XP install, Tutorial in PDF, pénzügyi előrejelzési applications) Trajan: http: //www. trajan-software. demon. co. uk/Downloads. htm (30 days shareware, GUI, Win XP install, Tutorial in HTML, no real application) AINet: http: //www. ainet-sp. si/NN/En/nn. htm (1 days shareware, GUI, Win 95 install, Tutorial in PDF, nincs még valós alkalmazása) Ne. Net: http: //koti. mbnet. fi/~phodju/nenet/Nenet/Download. html (performance limited shareware, GUI, Win 95 install, Tutorial in HTML, SOM networks oriented) Add-Ons for Statistical Packages: Statistica Neural Networks: https: //www. statsoft. com/downloads/maintenance/download. html (no shareware, GUI, Win XP install, Tutorial in MPEG)

References 4 Add-Ons for MATLAB: Matlab Neural Toolbox: http: //www. mathworks. com/products/neuralnet/ (No shareware) References 4 Add-Ons for MATLAB: Matlab Neural Toolbox: http: //www. mathworks. com/products/neuralnet/ (No shareware) SOM Tool. Box: http: //www. cis. hut. fi/projects/somtoolbox/download/ (Matlab 5, free, GUI, Tutorial in PDF) Fast. ICA: http: //www. cis. hut. fi/projects/ica/fastica/code/dlcode. shtml (Matlab 7, free, GUI, Tutorial in PDF) Net. Lab: http: //www. ncrg. aston. ac. uk/netlab/down. php (Matlab 5, free, GUI, Tutorial in PDF) NNSys. ID: http: //www. iau. dtu. dk/research/control/nnsysid. html (Matlab 7, free, GUI, Tutorial in PDF) Excel Add-Ins in Financial Forecasting: Neuro. Shell: http: //www. neuroshell. com/ (no shareware) Neuro. XL: http: //www. neuroxl. com/ (no shareware) Comparison of 50 commercial licensed neural software: http: //wwwcs. unipaderborn. de/~IFS/Tools/neural_network_tools. htm