情報学広場:情報処理学会電子図書館

2 min read Original article ↗

9e1431e2-99f7-4d16-8f82-d7dcfa6a2045

名前 / ファイル ライセンス アクション
IPSJ-GPWS2023012.pdf IPSJ-GPWS2023012.pdf (275.3 kB)

Copyright (c) 2023 by the Information Processing Society of Japan

オープンアクセス
Item type Symposium(1)
公開日 2023-11-10
タイトル
タイトル Playing Board Games with a Deep Convolutional Neural Network on the Motorola 6809 8-Bit Microprocessor
タイトル
言語 en
タイトル Playing Board Games with a Deep Convolutional Neural Network on the Motorola 6809 8-Bit Microprocessor
言語
言語 eng
キーワード
主題Scheme Other
主題 deep learning
キーワード
主題Scheme Other
主題 quantization
キーワード
主題Scheme Other
主題 neural networks
資源タイプ
資源タイプ識別子 http://purl.org/coar/resource_type/c_5794
資源タイプ conference paper
著者所属
Kayufu
著者所属(英)
en
Kayufu
著者名 Rémi, Coulom
Rémi, Coulom

Search repository

著者名(英) Rémi, Coulom
en Rémi, Coulom

Search repository

論文抄録
内容記述タイプ Other
内容記述 While training deep-learning neural networks often requires considerable amounts of computing power, inference is efficient, and can be run on small devices. Cell phones are a typical example, but they are still rather powerful. The research presented in this paper takes the challenge to the extreme by running a Go-playing convolutional neural network on the 6809 CPU, an 8-bit microprocessor launched by Motorola in 1978. The software was implemented on a Thomson MO5 microcomputer, and reached a playing strength on par with GNU Go.
論文抄録(英)
内容記述タイプ Other
内容記述 While training deep-learning neural networks often requires considerable amounts of computing power, inference is efficient, and can be run on small devices. Cell phones are a typical example, but they are still rather powerful. The research presented in this paper takes the challenge to the extreme by running a Go-playing convolutional neural network on the 6809 CPU, an 8-bit microprocessor launched by Motorola in 1978. The software was implemented on a Thomson MO5 microcomputer, and reached a playing strength on par with GNU Go.
書誌情報 ゲームプログラミングワークショップ2023論文集

巻 2023, p. 66-69, 発行日 2023-11-10

出版者
言語 ja
出版者 情報処理学会

Share

Cite as