Assignment 1 Solutions
1
Problem Modeling
1.1
Capital Budgeting (10 marks)
Variables: x1 , x2 , x3 and x4 are binary variables, representing the investment decisions of project 1,
2, 3, and 4. A value 1 indicating invest while a value 0 indicating dont in
1/16/14
Outline
CS 6776
Evolutionary Computation
Variable Length Representation, mostly
used to solve modeling type of problems.
Parse Tree
Graph
Finite State Machine
January 16, 2014
Unlike fixed-length representation, both
contents and structure of
Outline
CS 6776
Evolutionary Computation
January 21, 2014
Fitness Function
A mathematical function that quantifies
how good a solution is.
A problem can be modelled as a
maximization or a minimization problem.
Example:
TSP: A tour X = cfw_ x i , i = 1
Outline
CS 6776
Evolutionary Computation
January 14, 2014
Evolutionary Algorithms Workflow
Evolutionary Algorithms Design
Representations and Fitness Function
Problem Modeling
Fixed-length Representation: mostly used
for optimization type of problems
Outline
CS 6776
Evolutionary Computation
January 9, 2014
Course Introduction
Course website:
http:/www.cs.mun.ca/~tinayu/Teaching_files/
cs6776.html
Submit your assignments to D2L:
https:/online.mun.ca
No Text book is required. I will post lecture
no
Assignment 1
Due date: January 30, 2014
Type your answers and submit a printed hard copy.
Hand-written solutions are not accepted.
1
Problem Modeling
Your task is to frame the problem for an evolutionary algorithm to search for
a solution. For each questi
Assignment 2
Due date: February 20, 2014
Type your answers and submit a printed hard copy.
Hand-written solutions are not accepted.
Dont submit your program code.
1
Computer Exercises
The two-dimensional Rosenbrock function is dened as follows:
f (x1 , x2
Assignment 3 Part 1
Due date: March 6, 2014
Type your answers and submit a printed hard copy.
Hand-written solutions are not accepted.
Dont submit your program code.
1
Computer Exercises (60 marks)
The Rosenbrock function is dened as follows:
argmin f (X
Outline
Selection Methods
CS 6776
Evolutionary Computation
Stochastic Selection
Deterministic Selection
January 23, 2014
Evolutionary Algorithm Workflow
When to Select
Selection can occur at two stages of evolution:
Parent selection: select individua
Assignment 1 Computer Exercises
Suggested Discussions
2.1
CS-6776
Evolutionary Computation
January 27, 2014
Does the fitness of the best solution improves
monotonically under all selection methods?
Why or why not?
Does the population average fitness im
2/20/14
Contents
CS 6776
Evolu0onary Computa0on
February 20, 2014
PSO Review
A par0cle posi0on is updated using its
associated velocity.
Velocity can be viewed as the step size to
update the par0cle posi0on.
2/25/14
Final Project
Individual project:
CS6776
Evolu1onary Computa1on
February 25, 2014
Suggested Projects
Extension of one of your 4 assignments:
Solve one the the modeling problems in assignment 1,
using EA/PS
2/11/14
Mul/objec/ve Gene/c Algorithms
CS 6776
Evolu/onary Computa/on
K. Deb, A. Pratap, S. Agarwal and T. Meyarivan,
A Fast and Eli/st Mul/objec/ve Gene/c
Algorithm: NSGA II, IEEE Transac/ons on
Evolu/onary Computa
1/30/14
Outline
CS 6776 Evolu0onary
Computa0on
Assignment 1 typo corrected version is posted.
Varia0on operator: muta0on
January 30, 2014
Selec0ononly Model
Selec0on is exploita0on:
Under tnessbased selec0on, Ler
Outline
CS 6776
Evolutionary Computation
Exploration Vs. Exploitation
Exploration and Exploitation
Other Population Diversity Preservation
Techniques
February 6, 2014
Exploration vs. Exploitation
Exploration and Exploitation
Evolutionary search is com