Research

Application of Neural Networks in Video Game Simulation

Application of Neural Networks in Video Game Simulation

Application of Neural Networks in Video Game Simulation

By Biljana Tešić, Marko Marković and Katarina Marković

Abstract

“The subject of this paper is the development of 2D/3D video games using neural networks. The simulation method was used to design and program the video game Super Mario, which with its well-known functionality enables the application of artificial intelligence methods and neural networks. This paper aims to understand the relationship between the use of video games and their neural correlates, taking into account the whole range of cognitive factors that they include. The results of the research indicate the importance of using artificial neural networks in video games, bearing in mind that prediction is closely related to learning and that the existence of feedback allows game participants to evaluate their performance and increase the quality of future prediction of situations and moves. Despite the heterogeneity of the field of study, the research results indicate that it is possible to establish links between neural and cognitive aspects, especially in terms of attention, cognitive control, visual-spatial skills, cognitive load. However, many aspects could be improved. The lack of standardization in various aspects of video game-related research, such as participant characteristics, characteristics of each video game genre, and different goals, could contribute to disagreements with some related research.”

Reference

Tešić, B., Marković, M., &; Marković, K. (2022). Application of neural networks in video game simulation. Proceedings of the International Scientific Conference - Sinteza 2022. doi:10.15308/sinteza-2022-20-28 https://portal.sinteza.singidunum.ac.rs/paper/838

Keyword

Neural networks, video games, FeedForward, neuron, research