Genetic Algorithm Concepts and Working

Name: Genetic Algorithm Concepts and Working
Rating: 4.6 (82 reviews)

Created byDr.Deeba K

Last updated 1/2025

English

English [Auto],

What you'll learn

Explore the principles of Evolutionary Computation and delve into Genetic Algorithms.
Familiarize with the key terminologies and operators essential for Genetic Algorithm operation.
Advance understanding through the exploration of sophisticated operators and techniques within Genetic Algorithms.
Acquire practical skills by implementing Genetic Algorithms through simple Python code.
Discover real-world applications where Genetic Algorithms offer effective solutions.

Course content

4 sections • 17 lectures • 3h 19m total length

Introduction to the course on Genetic Algorithm2:37
Explore how genetic algorithms, a search-based optimization inspired by natural selection, evolve generations by fitness function evaluation, selecting the parental chromosome, applying crossover and mutation to find the best solutions.
History of Evolutionary Computing8:04
Explore the evolution-inspired genetic algorithm, tracing Darwin's survival of the fittest to Holland's 1960 invention, and learn how populations of solutions, fitness evaluation, crossover, and mutation drive optimization.
Terminologies in Genetic Algorithms9:33
Explore key genetic algorithm terminologies: chromosome, gene, locus, allele, genotype, phenotype, and population, along with encoding schemes, search space, objective function, and genetic operators like selection, crossover, and mutation.
Assessment 1 - Basic Terminologies

Flow of Working - Genetic Algorithm17:49
Learn how genetic algorithms encode problems into chromosome representations, initialize a random population, and evolve solutions via fitness-driven selection, crossover, and mutation across generations.
Example - Working of Genetic Algorithm25:59
Learn how a genetic algorithm solves optimization by encoding solutions as chromosomes, evaluating fitness, and evolving a population through selection, crossover, and mutation, with a binary encoding example.
Python code14:07
Assessment 2 - Working of Genetic Algorithm

Types of Encoding7:04
Explore encoding techniques in genetic algorithms, including binary, permutation, value, and three encoding, and learn to choose chromosome structures for problems like knapsack and traveling salesman.
Encoding Implementation3:13
Explore python-based encoding methods for genetic algorithms, including binary, permutation, octal, and hexadecimal encodings, using chromosome length and randomized generation of 0/1s or city sequences.
Types of Selection17:46
Compare selection methods in genetic algorithms—roulette wheel, rank-based, stochastic universal sampling, tournament, steady state, and elitism—driven by fitness or objective functions to optimize solutions.
Types of Crossover15:42
learn about crossover techniques in genetic algorithms, including single-point, two-point, multi-point, uniform crossover, and real, binary, permutation encodings, using PMX, cyclic, and order crossover methods to recombine parental genes.
Types of Mutation5:14
Understand how mutation in genetic algorithms alters single genes and explores new genes through bit flip, insertion, swap, scramble, and inversion, with script mutation for raw value encodings.
Mutation Implementation14:31
Explore genetic algorithm mutation techniques in Python, including bit flip, insertion (permutation encoding), random reset, swap, scrambled, and inversion mutations on binary chromosomes, with practical code and mutation points.
Assessment 3 - Techniques involved

Python Implementation of Genetic Algorithm11:26
Explore a Python implementation of a genetic algorithm that optimizes six real-valued weights using fitness-based selection, crossover, and mutation, with encoded population and neural-network inspired inputs.
Travelling Salesman Problem11:13
Learn how a genetic algorithm solves the traveling salesman problem by evolving city permutations to minimize distance, using a distance matrix and computation encoding.
Python Code for Genetic Algorithm12:48
Learn a Python genetic algorithm for the traveling salesman using permutation encoding, Euclidean distance, inverted fitness function, with tournament selection, ordered crossover, and swap mutation.
Neural Network Weight adjustment9:14
Explore how to use genetic algorithms to adjust neural network weights, encoding weight vectors, selecting parents, and applying crossover and mutation to maximize accuracy.
Python code for Neural Networks using GA13:16
Explore Python code for a neural network optimized by a genetic algorithm, covering weight initialization, sigmoid activation, mean square error, fitness maximization, and roulette wheel selection with single-point crossover.
Assessment 4 - Applications of Genetic Algorithm

Requirements

No prerequisites are there for this course. Students can listen to the lectures to understand Genetic Algorithm concepts from base.

Description

Genetic Algorithm is a search based optimization algorithm used to solve problems were traditional methods fails. It is an randomized algorithm where each step follows randomization principle.

Genetic Algorithm was developed by John Holland, from the University of Michigan, in 1960. He proposed this algorithm based on the Charles Darwin’s theory on Evolution of organism. Genetic Algorithm follows the principal of “Survival of Fittest”. Only the fittest individual has the possibility to survive to the next generation and hence when the generations evolve only the fittest individuals survive.

Genetic Algorithms operates on Solutions, hence called as search based optimization algorithm. It search for an optimal solution from the existing set of solutions in search space. The process of Genetic Algorithm is given as,

1. Randomly choose some individuals (Solutions) from the existing population

2. Calculate the fitness function

3. Choose the fittest individuals as parental chromosomes

4. Perform crossover (Recombination)

5. Perform Mutation

6. Repeat this process until the termination condition

This steps indicated that Genetic Algorithm is an Randomized, search based optimization Algorithm.

This course is divided into four modules.

First module – Introduction, history and terminologies used in Genetic Algorithm.

Second Module – Working of genetic algorithm with an example

Third Module – Types of Encoding, Selection, Crossover and Mutation methods

Fourth module – Coding and Applications of Genetic Algorithm

Happy Learning!!!

Who this course is for:

Computer science students
Students doing research in Genetic Algorithm
Students interested in understanding the basic working of Genetic Algorithm
Interested in Nature inspired computing
Planning to Explore Evolutionary Computing
Planning to Explore Optimization Techniques

Genetic Algorithm Concepts and Working

What you'll learn

Explore related topics

Course content

History and Inspiration of Genetic Algorithm3 lectures • 20min

Working of Genetic Algorithm3 lectures • 58min

Elements of Genetic Algorithm6 lectures • 1hr 4min

Applications of GA5 lectures • 58min

Requirements

Description

Who this course is for: