You are on page 1of 12

Geneticalgorithm

“Method to manipulate, calculate and solve problem”

12/08/2021
TheGeneticAlgorithm
INTRODUCTION
Directed search algorithms based on the mechanics of biological evolution

To understand the adaptive processes of natural systems

To design artificial systems software that retains the robustness of natural
systems

Provide efficient, effective techniques for optimization and machine


learning applications

Widely-used today in business, scientific and engineering circles

12/08/2021
DEFINITION
 Genetic algorithm (GA) is a search that mimics the
process of natural evolution. This heuristic is routinely
used to generate useful solutions
to optimization and search problems.

12/08/2021
ComponentsofaGA
A problem to solve, and ...
Encoding technique (gene, chromosome)
Initialization procedure (creation)
Evaluation function (environment)
Selection of parents (reproduction)
Genetic operators (mutation, recombination)
Parameter settings (practice and art)

12/08/2021
Ga cycle
children
reproduction modification
modified
parents children
population evaluation
evaluated children
deleted
members

discard

12/08/2021
Population :It can be any information , or data

Reproduction : it is carries out on the basis of problem

1. Mutation :deletion of ideas evaluated in reproduction

2. Crossing over : joining of genetic material on chromosomes

Evaluation: result of the problem

Deletion : discarding the problem

12/08/2021
EXAMPLE:
A SALES PERSON HAVE TO VISIT 9 CITIES .
Find a tour of a given set of cities so that
each city is visited only once
the total distance traveled is minimized

He will use the basic GA concepts such as :-


1. Representaion :by making points
2. Reproduction :introducing new trip methods

12/08/2021
Initialize population: no of cities
Evaluate problem: visit each city once
Not Satisfied: by his schedule
Elect parents for reproduction: ways to
decide
Perform recombination and mutation:
made various ways to travel
Evaluate population: finally result

12/08/2021
SOLUTION WITH GA ORDINARY SOLUTION

42 TSP30 (Performance = 652)


38 TSP30 Solution (Performance = 420)
35 120 120
26
21
35 100 100
32
7 80 80
38
46
44 y60
y 60
58
60 40
69 40
76
78 20
20
71
69
0
67 0
0 10 20 30 40 50 60 70 80 90 100
62 x 0 10 20 30 40 50 60 70 80 90 100
84 x
94

12/08/2021
BENEFITSOFGA
Concept is easy to understand
Modular, separate from application
Supports multi-objective optimization
Good for “noisy” environments
Always an answer; answer gets better with time
Inherently parallel; easily distributed

12/08/2021
PROBLEMTOGA
The search space is large, complex or poorly
understood
Domain knowledge is scarce or expert knowledge is
difficult to encode to narrow the search space
No mathematical analysis is available
Traditional search methods fail

12/08/2021
CONCLUSION
Genetic Algorithms are easy to apply to a wide range of
problems, from optimization problems like the
traveling salesperson problem, to inductive concept
learning, scheduling, and layout problems. The results
can be very good on some problems, and rather poor
on others

12/08/2021

You might also like