Artificial Neural Network Architecture Tuning Algorithm : доклад, тезисы доклада

Описание

Тип публикации: доклад, тезисы доклада, статья из сборника материалов конференций

Конференция: International Workshop “Hybrid methods of modeling and optimization in complex systems” (HMMOCS 2022); Krasnoyarsk; Krasnoyarsk

Год издания: 2022

Идентификатор DOI: 10.15405/epct.23021.29

Ключевые слова: optimization, artificial multilayer neural networks, genetic algorithm, classification, keras

Аннотация: In this paper, we will consider artificial neural networks, one of the most powerful methods of data analysis. For each individual task, the type of neural network changes, and its various parameters are selected, which takes too much time and resources. To avoid these shortcomings, a self-tuning algorithm for the architecture of tПоказать полностьюhe neural network was developed and implemented, due to the genetic algorithm. An artificial neural network has been implemented for data classification tasks. This implementation provides the ability to select the number of hidden layers in the artificial neural network, the number of neurons on each of the layers, the type of activation functions for each neuron of the network. Nfr of the implementation of this evolutionary algorithm is the different lengths of individuals in the population and the ability to manipulate it. A genetic algorithm has been implemented that allows coding all the parameters of the neural network discussed above. The algorithm was developed using the modern Keras neural network training library. The efficiency of the developed algorithms was compared with each other.

Ссылки на полный текст

Издание

Журнал: HYBRID METHODS OF MODELING AND OPTIMIZATION IN COMPLEX SYSTEMS

Номера страниц: 241-248

Место издания: London, United Kingdom

Издатель: European Proceedings

Персоны

  • Yurshin V. G. (Siberian Federal University)
  • Stanovov V. V. (Siberian Federal University)

Вхождение в базы данных