Introduction to Neural Networks and Fuzzy Logic at President University

introduction to neural networks and fuzzy logic n.w
1 / 27
Embed
Share

Explore the world of neural networks and fuzzy logic in this insightful lecture series by Dr.-Ing. Erwin Sitompul at President University. Dive into the principles of neural networks, fuzzy systems theory, and their applications with engaging textbooks. Understand the grading policy, including lecture notes, homework, presentations, quizzes, and exams, while ensuring timely submission of handwritten notes for maximum score. Enhance your learning through regular homework assignments and group projects. Don't miss this opportunity to delve into the fascinating field of neural networks and fuzzy logic.

  • Neural Networks
  • Fuzzy Logic
  • Lecture Series
  • President University
  • Homework Assignments
rayaanacharya
moto_ani Follow

Uploaded on | 0 Views

Download Presentation

Please find below an Image/Link to download the presentation.

The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author. If you encounter any issues during the download, it is possible that the publisher has removed the file from their server.

You are allowed to download the files provided on this website for personal or commercial use, subject to the condition that they are used lawfully. All files are the property of their respective owners.

Download Presentation

The content on the website is provided AS IS for your information and personal use only. It may not be sold, licensed, or shared on other websites without obtaining consent from the author.

E N D

Presentation Transcript

  1. Introduction to Neural Networks and Fuzzy Logic Lecture 1 Dr.-Ing. Erwin Sitompul President University http://zitompul.wordpress.com 2 0 2 1 President University Erwin Sitompul NNFL 1/1

  2. Introduction to Neural Networks and Fuzzy Logic Textbooks Textbook: Neural Networks. A Comprehensive Foundation , 2nd Edition, Simon Haykin, Prentice Hall, 1999. Fuzzy Systems Theory and Its Application , Toshiro Terano et. al., Academic Press, 1992. President University Erwin Sitompul NNFL 1/2

  3. Introduction to Neural Networks and Fuzzy Logic Grade Policy Final Grade = 10% Lecture Notes + 10% Homework + 20% Presentation/Paper + 20% Quizzes + 20% Mid Exam + 20% Final Exam + Extra Points Attendance will be counted. Maximum allowed lateness is 15 minutes. Only sickness with official paper proof will be counted as attending class. Only permission for duty with official paper proof will be counted as attending class. President University Erwin Sitompul NNFL 1/3

  4. Introduction to Neural Networks and Fuzzy Logic Grade Policy Final Grade = 10% Lecture Notes + 10% Homework + 20% Presentation/Paper + 20% Quizzes + 20% Mid Exam + 20% Final Exam + Extra Points You are expected to write a note along the lectures to record your own conclusions or materials which are not covered by the lecture slides. Your handwritten note should be uploaded to the Gdrive link given to you via email. DO NOT make subfolders. To get maximum score, upload the notes in 6 different days (3 different days before and 3 different days after mid-exam). The notes is to be submitted in picture format (JPG, GIF, etc). PDF is not allowed. Suggested file name format: NNFL.Name.XX.jpg. Example: NNFL.AndiK.01.jpg. Deadline of note submission: Sunday, 18 July 2021, 23:59. President University Erwin Sitompul NNFL 1/4

  5. Introduction to Neural Networks and Fuzzy Logic Grade Policy Homeworks will be given in fairly regular basis. The homework grades will be averaged. Homeworks can be typed or written. Homeworks are to be submitted on A4 papers, otherwise they will not be graded. Fuzzy Logic and Neural Networks Homework 2 Ito Chen 009202700008 21 March 2029 D6.2. Answer: . . . . . . . . Heading of Written Homework Papers (Required) President University Erwin Sitompul NNFL 1/5

  6. Introduction to Neural Networks and Fuzzy Logic Grade Policy Homeworks must be submitted via Google Classroom on time, one day before the schedule of the lecture. Late submitted homeworks will not be graded. Format of homework is free (PDF, DOC, JPG, GIF, etc). There will be 1 group assignment for paper writing. 14-19 June 2021 : Paper assignment 05-10 July 2021 : Presentation of preliminary results 25 July 2021 : Paper submission There will be 3 quizzes. Only the best 2 will be counted. Make up of quiz must be held within one week after the schedule of the respective quiz. Extra points will be given every time you solve a problem in front of the class or answer a question. You will earn 1 or 2 points. The updated version will be available on the lecture homepage around 1 days after class schedule. Please check regularly. http://zitompul.wordpress.com President University Erwin Sitompul NNFL 1/6

  7. Fuzzy Logic Introduction Meaning of fuzzy , Definition of Fuzzy Logic Covered with fuzz; Of or resembling fuzz; Not clear; indistinct A fuzzy recollection of past events. Not coherent; confused A fuzzy plan of action. Unclear, blurred, or distorted Some fuzzy pictures from a Russian radar probe. Fuzzy logic: a form of knowledge representation suitable for notions that cannot be defined precisely, but depend upon their contexts, it deals with reasoning that is approximate rather than fixed and exact. President University Erwin Sitompul NNFL 1/7

  8. Fuzzy Logic Introduction Origins of Fuzzy Logic The earliest record can be traced back as far as to the ancient Greece period Lotfi Zadeh (1965) The first to publish ideas of fuzzy logic Toshire Terano (1972) The first to organize a working group of fuzzy system F. L. Smidth et. al. The first to market fuzzy expert system President University Erwin Sitompul NNFL 1/8

  9. Fuzzy Logic Introduction 4 Seasons Spring Summer Autumn Winter 1 Membership 0.5 0 Time of the year President University Erwin Sitompul NNFL 1/9

  10. Fuzzy Logic Introduction Tall Persons 1 : A person is tall 0 : A person is not tall President University Erwin Sitompul NNFL 1/10

  11. Fuzzy Logic Introduction Room Temperature 1 : room is warm 0 : room is not warm Incorporation of human s perception President University Erwin Sitompul NNFL 1/11

  12. Fuzzy Logic Set Definition Classical Sets young = { x P | age(x) 20 } Characteristic function: 1, age( ) 0, age( ) 20 20 x x young = ( ) x A( ) x A= young 1 0 x = years x 20 President University Erwin Sitompul NNFL 1/12

  13. Fuzzy Logic Set Definition Fuzzy Sets Classical Logic Fuzzy Logic Element x belongs to set A with a certain degree of membership : (x) [0,1] Element x whether belongs to set A or not at all: (x) {0,1} A( ) x A( ) x A= young A= young 1 1 0 0 years x years x x = x = 21 21 President University Erwin Sitompul NNFL 1/13

  14. Fuzzy Logic Set Definition Fuzzy Sets Definition: Fuzzy Set A = {(x, A(x)) | x X, A(x) [0,1]} is defined by a universe of discourse x where 0 x 100 and a membership function A where A(x) [0,1] A( ) x A= young 1 = 0.4 A 0 years x x = 21 President University Erwin Sitompul NNFL 1/14

  15. Fuzzy Logic Set Definition Some Definitions Support of a fuzzy set A supp(A) = { x X | A(x) > 0 } Core of a fuzzy set A core(A) = { x X | A(x) = 1 } -cut of a fuzzy set A A = { x X | A(x) } (x) 1 = 0.6 0 x President University Erwin Sitompul NNFL 1/15

  16. Fuzzy Logic Fuzzy Logic Control Fuzzy Logic Control (FLC) Fuzzy Logic Control (FLC) may be viewed as a branch of intelligent control which serves as an emulator of human decision- making behaviour which is approximate rather than exact. FLC uses the IF-THEN rules, similar to binary control (Programmable Logic Controller, PLC). Rule Format: Ri: IF x is Aj AND y is Bk THEN z is Cl Ri: IF x is Aj OR y is Bk THEN z is Cl President University Erwin Sitompul NNFL 1/16

  17. Fuzzy Logic Fuzzy Logic Operators Logic Operators A B A B A B President University Erwin Sitompul NNFL 1/17

  18. Fuzzy Logic Fuzzy Logic Operators Boolean OR and Fuzzy OR Boolean OR Fuzzy OR p q 0 0.4 1 0.4 0.4 1 1 1 1 p 0 0 0 0.4 0.4 0.4 1 1 1 q 0 0.4 1 0 0.4 1 0 0.4 1 p q 0 1 1 1 p 0 0 1 1 q 0 1 0 1 President University Erwin Sitompul NNFL 1/18

  19. Fuzzy Logic Fuzzy Logic Operators Boolean AND and Fuzzy AND Boolean AND Fuzzy AND p^q 0 0 0 0 0.16 0.4 0 0.4 1 p 0 0 0 0.4 0.4 0.4 1 1 1 q 0 0.4 1 0 0.4 1 0 0.4 1 p^q 0 0 0 1 p 0 0 1 1 q 0 1 0 1 President University Erwin Sitompul NNFL 1/19

  20. Fuzzy Logic Fuzzy Logic Control Example: Air Fan Control (Single Input) Conventional (On-Off) Control: IF temperature > X C, THEN run fan, ELSE stop fan. Fuzzy Control: IF temperature is hot, THEN run fan at full speed; IF temperature is warm, THEN run fan at moderate speed; IF temperature is comfortable, THEN maintain fan speed; IF temperature is cool, THEN slow fan; IF temperature is cold, THEN stop fan. President University Erwin Sitompul NNFL 1/20

  21. Fuzzy Logic Fuzzy Logic Control Example: Heater Fan Control (Two Inputs) Problem: Change the speed of the fan, based on the room temperature and humidity. The temperature is classified into four conditions: Cold, Cool, Warm, and Hot. The humidity can be defined by: Low, Medium, and High. The available wattage settings of the heater fan are Zero, Low, Medium, and High. Temperature Humidity Fan Wattage President University Erwin Sitompul NNFL 1/21

  22. Fuzzy Logic Fuzzy Logic Control Example: Stopping A Car F m = = F my y Break force Mass of the car Initial position Initial velocity 13600 N = 0 N F 1500 kg 25 m = = m (0) (0) 10 m s y y President University Erwin Sitompul NNFL 1/22

  23. Fuzzy Logic Fuzzy Logic Control Example: Stopping A Car P-Control PD-Control + ( ) K e T e m = = F e K e w y w K e m p d = y p = , 0 K mT s K m y w K y m p = p p = = y + + 2 s K m p d p 2 n = With Kp = 240, the car will stop at the traffic light after 10 s. + + 2 2 n 2 s s n Choosing = 1, Td = 1, Kp = 6000, the car will stop at the traffic light after 5 s. President University Erwin Sitompul NNFL 1/23

  24. Fuzzy Logic Fuzzy Logic Control Example: Stopping A Car Fuzzy Logic Control: IF distance is long AND approach is fast, THEN brake zero; IF distance is long AND approach is slow, THEN brake zero; IF distance is short AND approach is fast, THEN brake hard; IF distance is short AND approach is slow, THEN brake zero. President University Erwin Sitompul NNFL 1/24

  25. Fuzzy Logic Fuzzy Logic Control Example: Stopping A Car Fuzzy Membership Functions 100 m 25 m 0 m 100 % ?? -100 m/s -10 m/s 0 m/s Negative to emphasize that the value is decreasing 100 % ?? 0 % 0 % President University Erwin Sitompul NNFL 1/25

  26. Fuzzy Logic Fuzzy Logic Control Example: Stopping A Car Time Response President University Erwin Sitompul NNFL 1/26

  27. Neural Networks Introduction Preparation Assignment Each of you should prepare a notebook for Quizzes and Exams. Ensure yourself to install Matlab in your computer, along with Matlab Simulink, Control System Toolbox, and Fuzzy Logic Toolbox. Quizzes, Midterm Exam, and Final Exam will be computer-based. The Fuzzy Logic Toolbox can be opened by typing fuzzy on the command window. Read the Fuzzy Toolbox Manual that can be found in the directory where Matlab is installed. One version of the manual can be found on the lecture website. President University Erwin Sitompul NNFL 1/27

Related


National Nuclear Forensics Library Development Overview

National Nuclear Forensics Library Development Overview

jay_li

More Related Content