Toward learning the causal layer of the Spatial Semantic Hierarchy using SOMs

Jefferson Provost, Patrick Beeson, and Benjamin J. Kuipers. Toward learning the causal layer of the Spatial Semantic Hierarchy using SOMs. In Symposium on Learning Grounded Representations, AAAI Spring Symposium Series, Stanford, CA, March 2001. AAAI Technical Report SS-01-05.

Abstract

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.

BibTeX

@InProceedings{Provost-sss-01,
  author =	 {Jefferson Provost and Patrick Beeson and Benjamin
                  J. Kuipers},
  title =	 {Toward learning the causal layer of the {Spatial
                  Semantic Hierarchy} using {SOMs}},
  booktitle =	 {Symposium on Learning Grounded Representations},
  year =	 2001,
  series =	 {AAAI Spring Symposium Series},
  address =	 {Stanford, CA},
  month =	 {March},
  note =	 {AAAI Technical Report SS-01-05.},
  abstract =	 {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.},
  bib2html_pubtype ={Workshop},
  bib2html_rescat ={Foundational Learning},
}

Download:

[242.1KB pdf]