Artificial Neural Network Architecture Tuning Algorithm
Abstract
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 the 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.
Copyright information
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
About this article
Publication Date
27 February 2023
Article Doi
eBook ISBN
978-1-80296-960-3
Publisher
European Publisher
Volume
1
Print ISBN (optional)
-
Edition Number
1st Edition
Pages
1-403
Subjects
Hybrid methods, modeling and optimization, complex systems, mathematical models, data mining, computational intelligence
Cite this article as:
Yurshin, V. G., & Stanovov, V. V. (2023). Artificial Neural Network Architecture Tuning Algorithm. In P. Stanimorovic, A. A. Stupina, E. Semenkin, & I. V. Kovalev (Eds.), Hybrid Methods of Modeling and Optimization in Complex Systems, vol 1. European Proceedings of Computers and Technology (pp. 241-248). European Publisher. https://doi.org/10.15405/epct.23021.29