Reference:

Jorge Letosa and Timo Honkela. Elementary Logical Reasoning in the SOM Output Space. In Proceedings of ICANN 2010, Artificial Neural Networks, pages 432–437. Springer, 2010.

Abstract:

In this paper, we consider how to represent world knowledge using the self-organizing map (SOM), how to use a simple recurrent network (SRN) to device sentence comprehension, and how to use the SOM output space to represent situations and facilitate grounded logical reasoning.

Suggested BibTeX entry:

@inproceedings{letosa2010elementary,
    author = {Jorge Letosa and Timo Honkela},
    booktitle = {Proceedings of ICANN 2010, Artificial Neural Networks},
    pages = {432--437},
    publisher = {Springer},
    title = {{Elementary Logical Reasoning in the SOM Output Space}},
    year = {2010},
}