メインナビゲーションにスキップ 検索にスキップ メインコンテンツにスキップ

Classification Performance in the Bio-inspired Asymmetric and Symmetric Networks

  • Naohiro Ishii
  • , Kazunori Iwata
  • , Naoto Mukai
  • , Kazuya Odagiri
  • , Tokuro Matsuo

研究成果: 書籍/レポート タイプへの寄稿会議への寄与

抄録

Recent developments of deep learning, machine learning, and artificial intelligence have a great influence on the wide areas of technologies. Classification is a core technology in their processing. This paper aims to make clear the classification performance for the bio-inspired asymmetric and symmetric networks. First, the bio-inspired asymmetric network is shown to have superior performance for tracing features compared to the symmetric one. Second, the classification characteristics of the asymmetric and symmetric networks are derived based on the independence of their outputs. Further, it is shown that generation of extended bases in the bio-inspired layered networks improves classification performance. Finally, the higher-dimensional mapping code generated as the extended bases are applied to the modified XOR problem.

本文言語英語
ホスト出版物のタイトルProceedings of 8th International Congress on Information and Communication Technology - ICICT 2023
編集者Xin-She Yang, R. Simon Sherratt, Nilanjan Dey, Amit Joshi
出版社Springer Science and Business Media Deutschland GmbH
ページ167-179
ページ数13
ISBN(印刷版)9789819932351
DOI
出版ステータス出版済み - 2024
外部発表はい
イベント8th International Congress on Information and Communication Technology, ICICT 2023 - London, 英国
継続期間: 20-02-202323-02-2023

出版物シリーズ

名前Lecture Notes in Networks and Systems
696 LNNS
ISSN(印刷版)2367-3370
ISSN(電子版)2367-3389

会議

会議8th International Congress on Information and Communication Technology, ICICT 2023
国/地域英国
CityLondon
Period20-02-2323-02-23

All Science Journal Classification (ASJC) codes

  • 制御およびシステム工学
  • 信号処理
  • コンピュータ ネットワークおよび通信

フィンガープリント

「Classification Performance in the Bio-inspired Asymmetric and Symmetric Networks」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル