IMPLEMENTING EVOLUTIONARY ALGORITHM INTO TRAINING SINGLE-LAYER ARTIFICIAL NEURAL NETWORK IN CLASSIFICATION TASK

• Autorzy: Płaczek Stanisław
• Języki publikacji: EN

Abstrakty

EN

The article proposes implementing a modified version of genetic algorithm in a neural network, what in literature is known as “evolutionary algorithm” or “evolutionary programming”. An Evolutionary Algorithm is a probabilistic algorithm that works in a set of weight variability of neurons and seeks the optimal value solution within a population of individuals, avoiding the local maximum. For chromosomes the real value variables and matrix structure are proposed to a single-layer neural network. Particular emphasis is put on mutation and crossover algorithms. What is also important in both genetic and evolutionary algorithms is the selection process. In the calculation example, the implementation of theoretical considerations to a classification task is demonstrated.

Słowa kluczowe

EN

Genetic Algorithm; Evolutionary Algorithm; selection process; mutation; recombination; replacement.

• Wydawca: Katedra Informatyki Szkoła Główna Gospodarstwa Wiejskiego w Warszawie
• Czasopismo: Information Systems in Management
• Rocznik: 2016
• Tom: 5
• Numer: 3
• Strony: 377-388

Daty

wydano

2016

Twórcy

autor

Płaczek Stanisław

• Faculty of Computer Science, Vistula University (AFiB Vistula)

Bibliografia

• A.E. Eiben, J.E. Smith: Introduction to Evolutionary Computing, Second Edition, Springer 2003, 2015.
• Michalewicz Z.: Genetic Algorithm + Data Structure = Evolutionary Programs, Springer – Verlag Berlin Haidelberg 1996.
• Montana DJ, Davis L,: "Training Feedforward Neural Network Using Genetic Algorithms. Proceedings of the 1989 International Join Conference on Artificial Intelligence", Morgan Kaufmann Publishers, San Mateo, CA, 1989.
• David E. Goldberg: Genetic Algorithms in Search, Optimization, and Machine Learning, Addison- Veslay Publishing Company, Inc. 1989.
• Xinjie Yu, Mitsuo Gen: Introduction to Evolutionary Algorithm, Springer London 2010.

Identyfikatory

ISSN

2084-5537