Research on Scalability of Neuron Circuit Using Adiabatic Quantum-Flux-Parametron Logic

カテゴリ：研究会(論文単位)

論文No：ECT25038

グループ名：【C】電子・情報・システム部門 電子回路研究会

発行日：2025/9/1

タイトル(英語)：Research on Scalability of Neuron Circuit Using Adiabatic Quantum-Flux-Parametron Logic

著者名：Zhang Zhichun(Tokyo City University),San Hao(Tokyo City University)

著者名(英語)： Zhichun Zhang(Tokyo City University),Hao San(Tokyo City University)

キーワード：

要約(日本語)：Neuron circuit using AQFP has been proposed. However, the scalability remains limited for practical applications. Building on prior work, we applied the previously introduced stochastic number representation to scale the neuron circuit from eight inputs to sixteen inputs. In addition, this work calculated the energy consumption of AQFP-based neuron circuits with input bits ranging from 2 to 16. This work addressed the lack of scalability and quantitative evaluation in existing AQFP neuron circuit designs.

要約(英語)：Neuron circuit using AQFP has been proposed. However, the scalability remains limited for practical applications. Building on prior work, we applied the previously introduced stochastic number representation to scale the neuron circuit from eight inputs to sixteen inputs. In addition, this work calculated the energy consumption of AQFP-based neuron circuits with input bits ranging from 2 to 16. This work addressed the lack of scalability and quantitative evaluation in existing AQFP neuron circuit designs.

本誌：2025年9月4日電子回路研究会

本誌掲載ページ：1-2p

原稿種別：英語

PDFファイルサイズ：569Kバイト