Publication Details
Title: A DSOM Hierarchical Model for Reflexive Processing: An Application to Visual Trajectory Classification
Author: C. Privitera and L. Shastri
Group: ICSI Technical Reports
Date: June 1996
PDF: ftp://ftp.icsi.berkeley.edu/pub/techreports/1996/tr-96-011.pdf
Overview:
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. Keywords: Dynamic Self-Organizing Map, Short-term Memory, Compositional Knowledge, Representation, Dynamics Bindings
Bibliographic Information:
ICSI Technical Report TR-96-011
Bibliographic Reference:
C. Privitera and L. Shastri. A DSOM Hierarchical Model for Reflexive Processing: An Application to Visual Trajectory Classification. ICSI Technical Report TR-96-011, June 1996
Author: C. Privitera and L. Shastri
Group: ICSI Technical Reports
Date: June 1996
PDF: ftp://ftp.icsi.berkeley.edu/pub/techreports/1996/tr-96-011.pdf
Overview:
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. Keywords: Dynamic Self-Organizing Map, Short-term Memory, Compositional Knowledge, Representation, Dynamics Bindings
Bibliographic Information:
ICSI Technical Report TR-96-011
Bibliographic Reference:
C. Privitera and L. Shastri. A DSOM Hierarchical Model for Reflexive Processing: An Application to Visual Trajectory Classification. ICSI Technical Report TR-96-011, June 1996