Proceedings of Annual Conference, Digital Game Research Association JAPAN
Online ISSN : 2758-6480
15th Annual Conference
Conference information

Application of Hopfield Networks to Character AI in Digital games
*Youichiro MIYAKE
Author information
CONFERENCE PROCEEDINGS OPEN ACCESS

Pages 112-114

Details
Abstract
Hopfield networks function as associative memory devices, and this research aims to use Hopfield networks to recall previously memorized image patterns in the dynamic environment of a digital game, and have the character AI perform actions in response. In this research, Hopfield networks are implemented as a character recognition function, and they are made to recognize the environment in a simple shooting game and take an action to defeat the enemy in response to the recognition. Such a recall mechanism in digital games should open up various possibilities for game design.
Content from these authors
© 2025 Digital Research Association JAPAN

この記事はクリエイティブ・コモンズ [表示 4.0 国際]ライセンスの下に提供されています。
https://creativecommons.org/licenses/by/4.0/deed.ja
Previous article Next article
feedback
Top