.png){kind=icon}
.png){kind=icon}
Return
A stable self-organized spatial pooling algorithm for hierarchical temporal memory
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2025.129049.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose a novel stable self-organized spatial pooling algorithm for Hierarchical Temporal Memory. • The developed SSO_HTM model can organize the learning columns according to the characteristics of the input data. • A stable column activation algorithm based on loadability is designed to improve the stability of the feature representation. • Our SSO_HTM model outperforms the baseline methods on various synthetic and real-world datasets.
Keywords:
stable self-organized spatial pooling
Hierarchical Temporal Memory
feature representation
column activation
learning columns
Journal
IF:
7.5
Papers:
2.9W
Citations:
10.2W
Organization
No organization information available