0% found this document useful (0 votes)
7 views3 pages

Soft Computing Problems

This document outlines study questions and implementation tasks across neural network design, mathematical calculations, fuzzy sets, and fuzzy relations. It includes specific tasks such as implementing logical operations using various models, performing net input calculations, and developing membership functions for fuzzy sets. Additionally, it covers operations like union and intersection for fuzzy sets, as well as defuzzification methods.

Uploaded by

aysha04.talrop
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
7 views3 pages

Soft Computing Problems

This document outlines study questions and implementation tasks across neural network design, mathematical calculations, fuzzy sets, and fuzzy relations. It includes specific tasks such as implementing logical operations using various models, performing net input calculations, and developing membership functions for fuzzy sets. Additionally, it covers operations like union and intersection for fuzzy sets, as well as defuzzification methods.

Uploaded by

aysha04.talrop
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

QUESTIONS AND IMPLEMENTATION TASKS

OVERVIEW
This document provides a comprehensive summary of study questions and implementation tasks,
categorized by their technical domain. It covers fundamental principles and mathematical
calculations across neural network design, network calculations, fuzzy sets, and fuzzy relation
systems.

1. NEURAL NETWORK DESIGN & IMPLEMENTATION

Logical AND Implementation

Design a Hebb network to implement logical AND using bipolar inputs and targets.

Implement logical AND using the McCulloch-Pitts (M-P) model with binary data.

Implement logical AND using a Genetic Algorithm (GA) approach where the
condition is w1x1 + w2x2 + b ≥ 5.

Logical OR Implementation

Design a Hebb network to implement logical OR using bipolar inputs and targets.

Using the linear separability concept, obtain the response for OR logic with bipolar
inputs and targets.

XOR & Specialized Functions

Implement the XOR function using McCulloch-Pitts neurons with binary data.

Use the Hebb rule to implement the XOR function.

Implement the AND NOT function using McCulloch-Pitts neurons with binary
data.

2. MATHEMATICAL & NETWORK CALCULATIONS

Net Input Calculations

Calculate the net input to the output neuron for a network with inputs x1 = 0.3, x2 =
0.5, x3 = 0.63 and weights w1 = 0.2, w2 = 0.1, w3 = -0.3.

Calculate the net input for a network that specifically includes a bias.
Activation & Learning Algorithms

Obtain the output of a neuron using binary sigmoidal (y = 1 / (1 + e-yin)) and


bipolar sigmoidal (y = 2 / (1 + e-yin) - 1) activation functions.

Implement one epoch of the Adaline algorithm for AND logic with initial weights
w1 = 0.2, w2 = 0.1 and learning rate α = 0.8.

Implement one epoch of the Perceptron learning algorithm for a logic gate.

Pattern Recognition

Using the Hebb rule, find the weights required to perform classification for a 3 × 3
input pattern where "+" represents 1 and empty space represents -1.

3. FUZZY SETS & OPERATIONS

Set Theory

Perform union, intersection, and complement for fuzzy sets A and B.

Find the algebraic sum, algebraic product, bounded sum, and bounded difference
for given sets.

For the fuzzy set A = { 0.1/2 + 0.4/3 + 0.5/4 + 0.6/5 + 1/7 + 1/8 + 0.5/9 }, find the
height, support, and core.

Membership Functions

Determine whether a fuzzy set defined by μA(x) is convex, normal, or subnormal


based on provided interval functions.

Calculate membership values for different triangle types (Isosceles, Right-angled,


Equilateral) for a triangle with angles 45°, 55°, 80°.

Linguistic Variables & Hedges

Develop membership functions for phrases like "very tall," "fairly tall," and "not
very short" using provided base sets.

Calculate values for linguistic hedges (e.g., "very A" as μ2).

4. FUZZY RELATIONS & SYSTEMS

Compositions & Products


Obtain the Max-Min and Max-Product compositions for given fuzzy relations R
and Q.

Perform Cartesian products over fuzzy sets and construct the relation R = M × N.

Lambda Cuts

For the set A = {(x1, 0.9), (x2, 0.5), (x3, 0.2), (x4, 0.3)}, find the cut for λ = 0.6.

Determine the crisp relation for a 3 × 3 matrix using λ-cuts at 0.1, 0.3, 0.7, and 0.9.

Defuzzification

Determine the defuzzified output value for a given membership function using
seven different methods (e.g., Centroid, Mean-max, weighted average).

You might also like