0% found this document useful (0 votes)
406 views2 pages

Soft Computing Question Bank

The document outlines important questions related to soft computing, covering topics such as the differences between hard and soft computing, fuzzy logic concepts, neural networks, genetic algorithms, and ANFIS architecture. It includes both theoretical questions and practical applications, along with comparisons between various learning methods and algorithms. The content is divided into two parts, with Part A focusing on definitions and concepts, and Part B delving into detailed explanations and examples.

Uploaded by

udayprasanna2004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
406 views2 pages

Soft Computing Question Bank

The document outlines important questions related to soft computing, covering topics such as the differences between hard and soft computing, fuzzy logic concepts, neural networks, genetic algorithms, and ANFIS architecture. It includes both theoretical questions and practical applications, along with comparisons between various learning methods and algorithms. The content is divided into two parts, with Part A focusing on definitions and concepts, and Part B delving into detailed explanations and examples.

Uploaded by

udayprasanna2004
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

CCS364-SOFT COMPUTING IMPORTANT QUESTION

PART-A

1.Differentiate hard computing And Soft computing .


2.What do you mean by defuzzification ?
3. What are the properties of fuzzy Relation?
4. What is the cardinality of fuzzy Set?
5.Explain Linguistic Variable.
6.Describe the term perceptron.
7.What is Backpropagation Algorithm?
8.What is perceptron Convergence theorem?
9. What is activation function?
10.Define supervised learning.
11.What two requirement should a problem satisfy it by a genetic algorithm ?
12. Define mutation rate.
13.Compare and Contract genetic algorithm with traditional algorithm.
14.Explain the “Darwinian theory of survival”.
15.List the Selection Operator
16. State Fuzzy Inference.
17.Explain dilemma between interpretability and precision.
18.Explain non-linear rule.
19.Why to use fuzzy logic in neural network ?
20.Explain ANFIS Architecture lst Layer.
21.Explain Advantages of fuzzy filtering.
22.What is function of input layer in neural network?
23.What is Fuzzy filtering neural networks?
24.Explain Plasma Spectrum Analysis.
25. Infer Neuro-Fuzzy model
PART-B

1.Explain Operations in fuzzy set With Examples.


2.Explain about the following defuzzification models
i)Sugeno fuzzy models.
ii)Tsukamoto Fuzzy models.
3.i)Explain single layer perceptron
ii)Compare Supervised learning and Unsupervised learning.
4.Explain Competitive learning in the Kohonen Self-Organizing networks
5.Expalin Genetic algorithm Concept.
6.Expalin Chromosome Encoding Schemes.
7.Expalin ANFIS Architecture
8.Expalin Neuro-fuzzy Spectrum.
9.Explain Soft computing for color Recipe prediction.
10.Explain plasma spectrum analysis and Hand written neural recognition.
11.membership function in fuzzy logic
12.Explain the concepts of fuzzy logicand how it differ from classical logic
13.differentiate supervised and unsupervised learning
14.Explain the concepts involved in handling the complex datasetb how SOM will helps
15.Explain the terminologies of genetic algorithm.
16.Explain the different types of encoding operation used in GA
17.Explain why ANFIS is considered as universal approximator
18.Explain the CANFIS model architecture.
19.Explaim about printed chara cter recognition application in detailed.
20.Explain plasma spectrum analysis.
21.Construct a perceptron to represent the Boolean fn AND with initial weight
w1=0.3,w2=0.2,learning rate=0.2,bias=0.4
22.Identify weight required to perfrom classification using perceptron n/w .The vectors(1,1,1,1)and
(-1,1,-1,-1)belongs to class(target value1) vectors(1,1,1,-1) and (1,-1,-1,1)not belongs.

You might also like