Scribd Logo
Upload

Welcome to Scribd!

  • 11 views

    Genetic Algorithm

    Uploaded by

    Anmol ahuja
    The document discusses genetic algorithms, including an overview of their history, important terms, how they work through fitness scoring, selection, crossover and mutation, and applications in areas like optimization problems, IoT, self-driving cars, image processing and machine learning.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    Genetic Algorithm

    Uploaded by

    Anmol ahuja
    11 views16 pages
    The document discusses genetic algorithms, including an overview of their history, important terms, how they work through fitness scoring, selection, crossover and mutation, and applications in areas like optimization problems, IoT, self-driving cars, image processing and machine learning.

    Original Description:

    Presentation on Genetic Algorihtm of Artificail Intelligence

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document discusses genetic algorithms, including an overview of their history, important terms, how they work through fitness scoring, selection, crossover and mutation, and applications in areas like optimization problems, IoT, self-driving cars, image processing and machine learning.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    11 views16 pages

    Genetic Algorithm

    Uploaded by

    Anmol ahuja
    The document discusses genetic algorithms, including an overview of their history, important terms, how they work through fitness scoring, selection, crossover and mutation, and applications in areas like optimization problems, IoT, self-driving cars, image processing and machine learning.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 16

    GENETIC ALGORITHMS

    Overview and its applications


    CONTENTS
    • Introduction

    • History

    • Important Terms

    • Fitness Score

    • Selection , Crossover and Mutation

    • Applications

    • Conclusion
    INTRODUCTION
    • Genetic algorithm has its foundation from biological natural evolution.
    • Basically, the purpose of the genetic algorithm is to provide high quality solution for search
    and optimization issues.
    • The selection of the fittest members of a population is the first step in the process of natural
    selection.
    • They produce offspring who will join the next generation and carry on their parents' genes.
    Better fitness means that offspring will outperform parents and have a higher probability of
    survival.
    • At the end of this iterative process, the generation with the highest level of fitness will be
    identified.
    H I STO RY
    • John Holland originally suggested using genetic algorithms to solve issues that would
    otherwise be impossible to solve computationally.
    • Darwin’s theory of evolution by genetic selection served as the original inspiration for
    Genetic Algorithms, a heuristic solution-search or optimization technique.
    • The building block hypothesis and Holland's Schema Theorem offered a theoretical and
    conceptual foundation for the creation of effective Genetic Algorithms.
    • As a result, the discipline expanded swiftly and the method was effectively used to solve a
    variety of real-world issues.
    WORKING OF
    GENETIC ALGORITHM
    How it works ?
    I M P O R TA N T T E R M S

    Individual Population Chromosome Gene Allele

    Solution to Set of all an individual variable Possible


    the problem individuals in population components settings for an
    that form individual
    chromosome
    EXAMPLE
    FUNCTIONALI
    TY OF
    GENETIC
    ALGORITHM
    FITNESS SCORE
    o Evaluation of Fitness Score is done for each individual in the population that indicates their
    level of "competence.“
    o The individuals with higher value of fitness score are given opportunity to reproduce and
    generate offspring.
    o The fittest individuals create superior kids by fusing the chromosomes of both parents.
    o Each new generation has better genes than the previous generation.
    o The population is said to have converged when new offspring show no desirable differences
    from those of earlier populations.
    SELECTION OF
    PA R E N T S
    Roulette Wheel Tournament Selection Rank based Selection
    Selection

    The method begins with Individuals are selected On the basis of their
    selecting a fixed point on into subgroups from the fitness value they are
    the wheel circumference, broader population, and given rank and thus, their
    rotating the wheel, and members of each selection entirely depends
    then choosing the parent subgroup engage in upon their rank and not
    on which the wheel stops. competition with one fitness
    another.
    CROSSOVER

    • Two individuals that are selected using Selection are used to produce off-springs using
    Crossover.
    • There are 2 different types of Crossover:

    One-Point Crossover Two-Point Crossover


    M U TAT I O N
    • Following crossover and selection, a new population of individuals is obtained. While some
    are created by crossover, others are just duplicated. Mutation is done to make sure that the
    individuals are not all precisely the same.
    • It basically flips one or more alley values of the chromosome.0 is flipped to 1 or 1 is flipped
    to 0 at random position in the chromosome.
    T E R M I N AT I O N
    • The algorithm will continue until a termination condition is encountered.
    • The new population will keep replacing the current population, and process will continue,
    regardless of whether the termination criteria are reached.
    • As a result, each population's best individual outcomes are determined.
    • Termination condition also varies from problem to problem.
    • For some, it may be convergence of population. For others it may be the best solution
    found, or, the expected size of population generated.
    A P P L I C AT I O N
    S
    • Solution to Optimization Problems
    • In IoT (Internet of Things)
    • Tesla’s Self-driving car
    • Vehicle Routing Optimization
    • Image Processing
    • Machine Learning
    • Robotics
    CONCLUSION

    Genetic Algorithm is a probabilistic method for optimizing problems


    that are based on a biological genetic assessment process. This
    technique is inspired by natural evolution. This piece of writing talks
    about Genetic algorithm, its implementation and application areas. It is
    a highly efficient algorithm for determining the global optimum
    solution to a wide range of problems
    THANK YOU
    Anmol Ahuja
    [email protected]

    You might also like