人工知能学会第二種研究会資料
Online ISSN : 2436-5556
STDPの学習への貢献
片山 淳安藤 慎吾島村 潤
著者情報
研究報告書・技術報告書 フリー

2021 年 2021 巻 AGI-019 号 p. 02-

詳細
抄録

STDP is known as a learning rule that represents Hebb's law because of its credibility and the simplicity of its mechanism confirmed by detailed experiments. Researchers who value physiological plausibility are challenging to carry out learning by STDP without adopting backpropagation. In this paper, we will introduce 6 of these challenging papers and consider how STDP contributes to learning.

著者関連情報
© 2021 著作者
前の記事 次の記事
feedback
Top