Course Name: Fuzzy Logic and Neural Networks

Course abstract

This course will start with a brief introduction to fuzzy sets. The differences between fuzzy sets and crisp sets will be identified. Various terms used in the fuzzy sets and the grammar of fuzzy sets will be discussed, in detail, with the help of some numerical examples. The working principles of two most popular applications of fuzzy sets, namely fuzzy reasoning and fuzzy clustering will be explained, and numerical examples will be solved. Fundamentals of neural networks and various learning methods will then be discussed. The principles of multi-layer feed forward neural network, radial basis function network, self-organizing map, counter-propagation neural network, recurrent neural network, deep learning neural network will be explained with appropriate numerical examples. The method of evolving optimized fuzzy reasoning tools, neural networks will be discussed with the help of some numerical examples. Two popular neuro-fuzzy systems will be explained and numerical examples will be solved. A summary of the course will be given at the end.


Course Instructor

Media Object

Prof. Dilip Kumar Pratihar

I received BE (Hons.) and M. Tech. from REC (NIT) Durgapur, India, in 1988 and 1994, respectively. I obtained my Ph.D. from IIT Kanpur, India, in 2000. I received University Gold Medal, A.M. Das Memorial Medal, Institution of Engineers’ (I) Medal, and others. I completed my post-doctoral studies in Japan and then, in Germany under the Alexander von Humboldt Fellowship Programme. I received Shastri Fellowship (Indo-Canadian) in 2019 and INSA Teachers’ Award 2020. I am working now as a Professor (HAG scale) of IIT Kharagpur, India. My research areas include robotics, soft computing and manufacturing science. I have published more than 275 papers and book-chapters. I have written the textbooks on “Soft Computing” and “Fundamentals of Robotics”, co-authored another textbook on “Analytical Engineering Mechanics”, edited a book on “Intelligent and Autonomous Systems”, co-authored reference books on “Modeling and Analysis of Six- legged Robots”; “Modeling and Simulations of Robotic Systems Using Soft Computing”; “Modeling and Analysis of Laser Metal Forming Processes by Finite Element and Soft Computing Methods” and “Multibody Dynamic Modeling of Multi-legged Robots”. My textbook on “Soft Computing” had been translated into Chinese language in 2009. I have guided 22 Ph.D.s. I am in editorial board of 10 International Journals. I have been elected as FIE, MASME and SMIEEE. I have completed a few sponsored (funded by DST, DAE, MHRD) and consultancy projects. I have filed two patents.
More info

Teaching Assistant(s)

No teaching assistant data available for this course yet
 Course Duration : Feb-Apr 2021

  View Course

 Syllabus

 Enrollment : 18-Nov-2020 to 15-Feb-2021

 Exam registration : 15-Jan-2021 to 12-Mar-2021

 Exam Date : 25-Apr-2021

Enrolled

1988

Registered

140

Certificate Eligible

84

Certified Category Count

Gold

15

Silver

27

Elite

32

Successfully completed

10

Participation

7

Success

Elite

Silver

Gold





Legend

AVERAGE ASSIGNMENT SCORE >=10/25 AND EXAM SCORE >= 30/75 AND FINAL SCORE >=40
BASED ON THE FINAL SCORE, Certificate criteria will be as below:
>=90 - Elite + Gold
75-89 -Elite + Silver
>=60 - Elite
40-59 - Successfully Completed

Final Score Calculation Logic

  • Assignment Score = Average of best 6 out of 8 assignments.
  • Final Score(Score on Certificate)= 75% of Exam Score + 25% of Assignment Score
Note:
We have taken best assignment score from both Jan 2020 and Jan2021 course
Fuzzy Logic and Neural Networks - Toppers list

N KAMALA 97%

JAIN (DEEMED-TO-BE UNIVERSITY)

DR JITENDRA KUMAR JAIN 94%

GOVERNMENT ENGINEERING COLLEGE BIKANER

RAJIB MAJUMDER 94%

TECHNO INTERNATIONAL NEW TOWN

JOSE M J 93%

GOVERNMENT COLLEGE OF ENGINEERING, KANNUR

DR RAMKRISHNA DANDAPAT 92%

VEER SURENDRA SAI UNIVERSITY OF TECHNOLOGY, BURLA

Enrollment Statistics

Total Enrollment: 1988

Registration Statistics

Total Registration : 140

Assignment Statistics




Assignment

Exam score

Final score

Score Distribution Graph - Legend

Assignment Score: Distribution of average scores garnered by students per assignment.
Exam Score : Distribution of the final exam score of students.
Final Score : Distribution of the combined score of assignments and final exam, based on the score logic.