Yuri R. Tsoy, Vladimir G. Spitsyn, Department of Computer Engineering icon

Yuri R. Tsoy, Vladimir G. Spitsyn, Department of Computer Engineering



НазваниеYuri R. Tsoy, Vladimir G. Spitsyn, Department of Computer Engineering
Дата конвертации25.10.2012
Размер445 b.
ТипДокументы


USING GENETIC ALGORITHM WITH ADAPTIVE MUTATION MECHANISM FOR NEURAL NETWORKS DESIGN AND TRAINING

  • Yuri R. Tsoy, Vladimir G. Spitsyn,

  • Department of Computer Engineering

  • Tomsk Polytechnic University

  • http://qai.narod.ru

  • neuroevolution@mail.ru


Report contents

  • 1. Introduction

  • 2. Description of the algorithm

  • 3. Adaptive mutation mechanism

  • 4. Results of experiments

  • 5. Implementation

  • 6. Conclusion



1.Genetic algorithms and neural networks

  • Genetic algorithms (GAs) use evolutionary concept (heredity, mutability and natural selection) to solve optimization tasks.

  • The idea of Artificial neural networks (ANNs) is inspired by functionality of human brain. ANNs are often used to solve classification and approximation tasks



1. Use of neural networks





2. Description of the algorithm



3. Adaptive mechanism of mutation





3. Adaptive mechanism of mutation





4. Results of experiments







4. Future plans

  • “Parameterless” variant of NEvA with adaptive mutation mechanism and adaptive population sizing.

  • Some preliminary results:



5. Implementation

  • The introduced algorithm is implemented to comply with the architecture of the software environment “GA Workshop”



5. “GA Workshop”

  • At the time “GA Workshop” is under construction (there is no GUI), although it is already possible to use it for researches. The following researches have been done:

  • Experiments with NEvA.

  • Study of quasi-species model by M. Eugen.

  • Study of majoring model by V.G. Red’ko.

  • Investigation of simple population sizing techniques.

  • Numerical optimization with use genetic algorithm.

  • Experiments with compensatory genetic algorithm.



Features:

  • Features:

  • 3 different variants of genetic algorithm, including “standard” GA, compensatory GA and NEvA;

  • 5 different crossover operators for the binary encoded GA and 4 different crossover operators for NEvA;

  • 4 selection strategies;

  • 13 benchmark problems;

  • 3 different population sizing strategies;



Data available for analysis:

  • Data available for analysis:

  • Data that describes each generation of GA (fitness distribution for each generation averaged over multiple launches).

  • Data that describes GA behavior (dynamics of averaged mean, the best and the worst fitness value for each generation, dynamics of averaged deviation of fitness, time per launch in milliseconds).

  • Data that describes obtained solutions (number of object function calculations until solution is found, time until the first solution is found in milliseconds. All solutions and some data describing additional properties of the solutions are output into separate file for further analysis and use)



Conclusion

  • Results of experiments showed that NEvA performance is comparable and in some cases surpass results of other algorithms for the reviewed problems (XOR problem and full information pole balancing)

  • Adaptive mutation rate caused increase of performance in comparison with NEvA with fixed Pm (up to 40% for 2-pole balancing task), although resulting networks were slightly worse for 1-pole balancing problems.



Thank you for your attention!





Похожие:

Yuri R. Tsoy, Vladimir G. Spitsyn, Department of Computer Engineering iconYuri R. Tsoy, Vladimir G. Spitsyn, Department of Computer Engineering

Yuri R. Tsoy, Vladimir G. Spitsyn, Department of Computer Engineering iconA compensatory genetic algorithm yuri R. Tsoy, Vladimir G. Spitsyn

Yuri R. Tsoy, Vladimir G. Spitsyn, Department of Computer Engineering iconThe results of theoretical research Vladimir Fedorovich Vlasov Science, Physics, Head of Research Department

Yuri R. Tsoy, Vladimir G. Spitsyn, Department of Computer Engineering iconLecture No. 1
Яковлев А. И., Doctor of Engineering Science, professor, academician of the Russian and International Engineering Academies, on a...
Yuri R. Tsoy, Vladimir G. Spitsyn, Department of Computer Engineering iconTsoy cai2010

Yuri R. Tsoy, Vladimir G. Spitsyn, Department of Computer Engineering iconBy Yury Tsoy look for updates at

Yuri R. Tsoy, Vladimir G. Spitsyn, Department of Computer Engineering iconYuri Gagarin

Yuri R. Tsoy, Vladimir G. Spitsyn, Department of Computer Engineering iconDigital-atv the Microwave Engineering Project

Yuri R. Tsoy, Vladimir G. Spitsyn, Department of Computer Engineering iconAnna Gabets, the English Language Department, instructor, meets Emmet Ryan

Yuri R. Tsoy, Vladimir G. Spitsyn, Department of Computer Engineering iconUkrainian Department of Education and Science Schmalhausen Institute of Zoology National Academy of Sciences of Ukraine

Разместите кнопку на своём сайте:
Документы


База данных защищена авторским правом ©podelise.ru 2000-2014
При копировании материала обязательно указание активной ссылки открытой для индексации.
обратиться к администрации
Документы

Разработка сайта — Веб студия Адаманов