Toward Learning the Causal Layer of the Spatial Semantic Hierarchy using SOMs (2001)
The Spatial Semantic Hierarchy (SSH) is a multi-level representation of the cognitive map used for navigation in largescale space. We propose a method for learning a portion of this representation, specifically, the representation of views in the causal level of the SSH using self-organizing neural networks (SOMs). We describe the criteria that a good view representation should meet, and why SOMs are a promising view representation. Our preliminary experimental results indicate that SOMs show promise as a view representation, though there are still some problems to be resolved.
In AAAI Spring Symposium Series, Learning Grounded Representations, 2001.

Patrick Beeson pbeeson [at] traclabs com
Benjamin Kuipers kuipers [at] cs utexas edu
Jefferson Provost Ph.D. Alumni jefferson provost [at] gmail com