Scribd
Upload
20 views

soft computing roadmap

Uploaded by

mohdali210783
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
20 views

soft computing roadmap

Uploaded by

mohdali210783
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

PRIORITY WISE UNITS AND TOPICS/QUESTIONS BASED ON FREQEUNCY

SOFT COMPUTING – IT – 701


Unit priority: 2>4>5>3>1

Unit I: Introduction to Neural Networks

• High Importance:
1. Compare artificial neural networks with biological neural networks.
2. Explain the McCulloch-Pitts model and compare it with biological neural
networks.
3. What is activation function in neural networks? Explain various activation
functions.
4. Define supervised and unsupervised learning. Provide examples.
5. Use McCulloch-Pitts neuron to design OR and AND logic functions.
6. Explain the concept of linear separability. Justify the XOR problem by a
single decision boundary.
• Moderate Importance:
1. Describe feedforward and feedback networks.
2. Explain the Hebb rule and its application.

Unit II: Supervised Learning

• High Importance:
1. Explain back propagation networks, their characteristics, and applications.
2. With the help of a block diagram, explain multilayer perceptrons and their
differences from single-layer networks.
3. Define Adaline and Madaline. Discuss the Delta rule with examples.
4. Discuss the application of neural networks in image compression.
• Moderate Importance:
1. State the importance of back propagation algorithms and their learning factors.
2. Write short notes on:
▪ RBFN (Radial Basis Function Network)
▪ Learning algorithm of perceptrons.

Unit III: Unsupervised Learning

• High Importance:
1. Explain Kohonen’s Self-Organizing Maps (SOM) network with its
architecture and flowchart.
2. Describe the architecture and algorithm of counter propagation networks
(CPN) with a diagram.
3. Write short notes on:
▪ Convolutional Neural Networks (CNNs)
▪ Recurrent Neural Networks (RNNs)
• Moderate Importance:
1. What is ART? Apply an ART algorithm to given data.

Unit IV: Fuzzy Sets

• High Importance:
1. Define membership functions and their importance in fuzzy logic.
2. Explain the Fuzzy Inference System (FIS). List its methods and compare
Mamdani and Sugeno systems.
3. Discuss fuzzy set operations (union, intersection, difference, complement)
with examples.
4. Write short notes on:
▪ Fuzzy if-then rules
▪ Defuzzification methods.
• Moderate Importance:
1. Explain any one application of fuzzy logic in solving engineering problems.
2. Perform operations on two fuzzy sets (union, intersection, etc.).

Unit V: Genetic Algorithms (GA)

• High Importance:
1. Define Population, Chromosome, Gene, Allele, Genotype, and Phenotype.
2. Explain the Schema theorem in GA.
3. Discuss various crossover and mutation techniques in GA.
4. Solve optimization problems using GA (e.g., maximize the function
f(x)=x2f(x) = x^2f(x)=x2).
• Moderate Importance:
1. Write short notes on:
▪ Ant Colony Optimization (ACO)
▪ Particle Swarm Optimization (PSO)
▪ Operators of GA.
2. Explain the Travelling Salesman Problem (TSP) and its solution using GA.

Topic Importance Summary

• Critical Focus Areas:


o Backpropagation networks
o Kohonen SOM and CPN
o Fuzzy Inference Systems and Defuzzification
o Schema theorem and optimization problems in GA.
• Supporting Topics:
o McCulloch-Pitts model, XOR problem, activation functions.
o Adaline/Madaline, Delta rule, supervised/unsupervised learning.
o Genetic algorithms and their operators.

You might also like