The Influence of Genetic Algorithms on Learning Possibilities of Artificial Neural Networks

Abstract

The presented research study focuses on demonstrating the learning ability of a neural network using a genetic algorithm and finding the most suitable neural network topology for solving a demonstration problem. The network topology is significantly dependent on the level of generalization. More robust topology of a neural network is usually more suitable for particular details in the training set and it loses the ability to abstract general information. Therefore, we often design the network topology by taking into the account the required generalization, rather than the aspect of theoretical calculations. The next part of the article presents research whether a modification of the parameters of the genetic algorithm can achieve optimization and acceleration of the neural network learning process. The function of the neural network and its learning by using the genetic algorithm is demonstrated in a program for solving a computer game. The research focuses mainly on the assessment of the influence of changes in neural networks’ topology and changes in parameters in genetic algorithm on the achieved results and speed of neural network training. The achieved results are statistically presented and compared depending on the network topology and changes in the learning algorithm.

Development of a Genetic Algorithm – Artificial Neural Network model to optimize the Dimensional Accuracy of parts printed by FFF

“…Details for ANN are well established and are provided in a number of references (Oreški and Andročec, 2020; Abdolrasol et al. , 2021; Kotyrba et al. , 2022).…”

“…Therefore, a discrete function can be handled without additional cost (Rajasekaran and Pai, 2003; Oreški and Andročec, 2020; Abdolrasol et al. , 2021; Kotyrba et al. , 2022).…”

“…The concept of ML is the ability of the computer to understand the structure of data by using a mathematical or statistical model (Patel et al, 2021). Details for ANN are well established and are provided in a number of references (Oreški and Androc ˇec, 2020;Abdolrasol et al, 2021;Kotyrba et al, 2022).…”

“…This causes discretization of the search space even though the function is a continuous one. Therefore, a discrete function can be handled without additional cost (Rajasekaran and Pai, 2003;Oreški and Androc ˇec, 2020;Abdolrasol et al, 2021;Kotyrba et al, 2022).…”

A Multi-Strategy Improved Arithmetic Optimization Algorithm

“…Therefore, extensive research has been conducted on swarm intelligence algorithms in recent years. Inspired by the laws underlying the development of natural things, some examples of these algorithms are the teaching and learning optimization algorithm (TLBO) [1], the positive chord algorithm (SCA) [2,3], the particle swarm optimization (PSO) [4][5][6], and the genetic algorithm (GA) [7,8]. They can also be inspired by the collective or social intelligence of natural biology, as in the case of the Harris hawks algorithm (HHO) [9,10], the artificial fish swarm algorithm (FSA) [11], the sparrow search algorithm (CSA) [12][13][14], and the gray wolf optimization algorithm (GWO) [15].…”