Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
7 views3 pages

EC Crossover and Mutation On A Giving Functions

The document outlines Quiz #1 for an Evolutionary Computing course, detailing questions on evolutionary algorithms, selection methods, and optimization concepts. It includes specific tasks such as initializing a population, calculating fitness values, applying selection, crossover, mutation, and truncation for survival selection. The final surviving population for the next generation is provided in both binary and decimal formats.

Uploaded by

muhammad.asadullah.suhail
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
7 views3 pages

EC Crossover and Mutation On A Giving Functions

The document outlines Quiz #1 for an Evolutionary Computing course, detailing questions on evolutionary algorithms, selection methods, and optimization concepts. It includes specific tasks such as initializing a population, calculating fitness values, applying selection, crossover, mutation, and truncation for survival selection. The final surviving population for the next generation is provided in both binary and decimal formats.

Uploaded by

muhammad.asadullah.suhail
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
You are on page 1/ 3

Evolutionary Computing Spring 2025

Quiz # 1
Marks : 10 Time:40 min

Name: Muhammad Nehal Ashfaq


Roll No: 21-F BSCS 09
Instructor: Dr. Asma Sanam Larik
Question #1:

a) List down the basic steps of an Evolutionary Algorithm?

• Initialization
• Evaluation
• Selection
• Crossover
• Mutation
• Survivor Selection
• Termination.

b) What are the advantages of Tournament Selection over Fitness Proportion Selection?

1) Prevents premature convergence


2) Provides better control over selection pressure
3) Handles negative and non-normalized fitness values effectively
4) Less affected by scaling issues:

c) What is suboptimal solution?

A suboptimal solution is one that is not the best possible outcome but is still
acceptable. It occurs when an algorithm finds a solution that is better than others but
not necessarily the global optimum.

d) What is a premature convergence?

Premature convergence occurs when a population loses diversity too soon and gets stuck in a
local optimum rather than exploring better solutions. This can result from excessive selection
pressure, low mutation rates, or overly exploitative search strategies.

Question #2:
Let f(x)= x2 be the function that we want to maximize
a. Initialize population with x= {3,5,2,1,9,7} . Represent it in binary.

3=0011
5=0101
2=0010
1=0001
9=1001
7=0111

Calculate fitness values:


f(3)=9, f(5)=25 , f(2)=4, f(1)=1, f(9)=81, f(7)=49
Compute total fitness:
9+25+4+1+81+49=169

Determine selection probability for each individual (FPS method):


P(3)=9/169
P(5)=25/169
P(2)=4/169
P(1)=1/169
P(9)=81/169
P(7)=49/169

Cumulative probabilities (for RBS):


3→0.053
5→0.201
2→0.225
1→0.231
9→0.711
7→1.0
Using the given random numbers {0.2, 0.4, 0.12, 0.6, 0.33, 0.9}, selection
results are:

0.2 → 5
0.4 → 9
0.12 → 3
0.6 → 9
0.33 → 9
0.9 → 7
New selected population: {5, 9, 3, 9, 9, 7}
Binary representation: {0101, 1001, 0011, 1001, 1001, 0111}

b. Apply crossover with one point bit flip.

Choose a crossover point (e.g., after the 2nd bit):


(01∣01) (10∣01) ⇒ (01∣01),(10∣01) (No change)
(00∣11) (10∣01) ⇒ (00∣01),(10∣11)
(01∣11) (01|11) ⇒ (10∣11),(01∣01)

New population: {0101, 1001, 0001, 1011, 1011, 0101}

c. Apply swap mutation

0101 → 0001
1001 → 1101
0001 → 0100
1011 → 0011
1011 → 0011
0101 → 0001
Mutated population: {0001, 1101, 0100, 0011, 0011, 0001}

d. Apply Truncation as Survival Selection

Sort individuals based on fitness and retain only the best ones:
f(0001)=1,
f(1101)=169,
f(0100)=16,
f(0011)=9,
f(0011)=9,
f(0001)=1,
f(0001) =1
Sorted order: 1101, 0100, 0011, 0011, 0001, 0001
After truncation (keeping the top 4 individuals):
Final population: {1101, 0100, 0011, 0011}

e. Write down the population that survives for the next generation.

Binary: {1101, 0100, 0011, 0011}


Decimal: {13, 4, 3, 3}
This final set of individuals moves to the next generation.

Good Luck

You might also like