Understanding SyncMap: Analyzing the components of Its Dynamical Equation

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

SycnMap has been recently proposed as an unsupervised approach to perform chunking. This model, which falls under the paradigm of self-organizing dynamical equations, can achieve learning merely using the principle of self-organization without any objective function. However, it is still poorly understood due to its novelty. Here, we provide a comprehensive analysis of the underlying dynamical equation that governed the learning of SyncMap. We first introduce several components of the dynamical equation: (1) Learning rate, (2) Dynamic noise, and (3) Coefficient of attraction force; As well as model-specific variables: (4) Input signal noise and (5) Dimension of weight space. With that, we examine their effect on the performance of SyncMap. Our study shows that the dynamic noise and dimension of weight space play an important role in the dynamical equation; By solely tuning them, the enhanced model can outperform the baseline methods as well as the original SyncMap in 6 out of 7 environments.

本文言語英語
ホスト出版物のタイトルProceedings of the 2022 5th Artificial Intelligence and Cloud Computing Conference, AICCC 2022
出版社Association for Computing Machinery
ページ246-254
ページ数9
ISBN(電子版)9781450398749
DOI
出版ステータス出版済み - 12月 17 2022
イベント5th Artificial Intelligence and Cloud Computing Conference, AICCC 2022 - Osaka, 日本
継続期間: 12月 17 202212月 19 2022

出版物シリーズ

名前ACM International Conference Proceeding Series

会議

会議5th Artificial Intelligence and Cloud Computing Conference, AICCC 2022
国/地域日本
CityOsaka
Period12/17/2212/19/22

!!!All Science Journal Classification (ASJC) codes

  • 人間とコンピュータの相互作用
  • コンピュータ ネットワークおよび通信
  • コンピュータ ビジョンおよびパターン認識
  • ソフトウェア

フィンガープリント

「Understanding SyncMap: Analyzing the components of Its Dynamical Equation」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