A Two-Layer Self-Organizing Map with Vector Symbolic Architecture for Spatiotemporal Sequence Learning and Prediction

A Two-Layer Self-Organizing Map with Vector Symbolic Architecture for Spatiotemporal Sequence Learning and Prediction

We propose a new nature- and neuro-science-inspired algorithm for spatiotemporal learning and prediction based on sequential recall and vector symbolic architecture. A key novelty is the learning of spatial and temporal patterns as decoupled concepts where the temporal pattern sequences are construc...

Full description

Bibliographic Details
Main Authors: Thimal Kempitiya, Damminda Alahakoon, Evgeny Osipov, Sachin Kahawala, Daswin De Silva
Format: Article
Language:English
Published: MDPI AG 2024-03-01
Series:Biomimetics
Subjects:
self-organizing maps
spatiotemporal sequence learning
vector symbolic architectures
hierarchical temporal memory
Online Access:https://www.mdpi.com/2313-7673/9/3/175

Internet

https://www.mdpi.com/2313-7673/9/3/175

Similar Items