In this paper, the abstract computational principles underlying topographic maps are discussed. We give a definition of a “perfectly neighbourhood preserving” map, which we call a
topographic homeomorphism, and we prove that this has certain desirable properties. It is argued that when a topographic homeomorphism does not exist (the usual case), many equally
valid choices are available for quantifying the quality of a map. We introduce a particular
measure that encompasses several previous proposals, and discuss its relation to other work.
This formulation of the problem sets it within the well-known class of quadratic assignment
problems.
%0 Conference Paper
%1 GoodhillEtAl1995
%A Goodhill, G.J.
%A Finch, S.
%A Sejnowski, T.J.
%B Proc. 2nd Joint Symp. on Neural Computation
%D 1995
%K dimensionalityreduction mapformation selforganization
%P 191--202
%T A unifying measure for neighbourhood preservation in topographic mappings
%X In this paper, the abstract computational principles underlying topographic maps are discussed. We give a definition of a “perfectly neighbourhood preserving” map, which we call a
topographic homeomorphism, and we prove that this has certain desirable properties. It is argued that when a topographic homeomorphism does not exist (the usual case), many equally
valid choices are available for quantifying the quality of a map. We introduce a particular
measure that encompasses several previous proposals, and discuss its relation to other work.
This formulation of the problem sets it within the well-known class of quadratic assignment
problems.
@inproceedings{GoodhillEtAl1995,
abstract = {In this paper, the abstract computational principles underlying topographic maps are discussed. We give a definition of a “perfectly neighbourhood preserving” map, which we call a
topographic homeomorphism, and we prove that this has certain desirable properties. It is argued that when a topographic homeomorphism does not exist (the usual case), many equally
valid choices are available for quantifying the quality of a map. We introduce a particular
measure that encompasses several previous proposals, and discuss its relation to other work.
This formulation of the problem sets it within the well-known class of quadratic assignment
problems.
},
added-at = {2008-05-12T14:04:26.000+0200},
author = {Goodhill, G.J. and Finch, S. and Sejnowski, T.J.},
biburl = {https://www.bibsonomy.org/bibtex/29b9a2eae063f9ce20f09246484d8db9d/tmalsburg},
booktitle = {Proc. 2nd Joint Symp. on Neural Computation},
interhash = {39a5ec4759d9bebf5c43f19ebdbef74e},
intrahash = {9b9a2eae063f9ce20f09246484d8db9d},
keywords = {dimensionalityreduction mapformation selforganization},
pages = {191--202},
timestamp = {2008-05-12T14:05:15.000+0200},
title = {{A unifying measure for neighbourhood preservation in topographic mappings}},
year = 1995
}