A DSOM Hierarchical Model for Reflexive Processing: An Application to Visual Trajectory Classification

TitleA DSOM Hierarchical Model for Reflexive Processing: An Application to Visual Trajectory Classification
Publication TypeTechnical Report
Year of Publication1996
AuthorsPrivitera, C. M., & Shastri L.
Other Numbers1021
KeywordsCompositional Knowledge, Dynamic Self-Organizing Map, Dynamics Bindings, Representation, Short-term Memory
Abstract

Any intelligent system, whether human or robotic, must be capable of dealing with patterns over time. Temporal pattern processing can be achieved if the system has a short-term memory capacity (STM) so that different representations can be maintained for some time. In this work we propose a neural model wherein STM is realized by leaky integrators in a self-organizing system. The model exhibits compositionality, that is, it has the ability to extract and construct progressively complex and structured associations in an hierarchical manner, starting with basic and primitive (temporal) elements. An important feature of the proposed model is the use of temporal correlations to express dynamic bindings.

URLhttp://www.icsi.berkeley.edu/ftp/global/pub/techreports/1996/tr-96-011.pdf
Bibliographic Notes

ICSI Technical Report TR-96-011

Abbreviated Authors

C. Privitera and L. Shastri

ICSI Publication Type

Technical Report