%0 Journal Article %1 szepesvari1994d %A Szepesvári, Cs. %A Balázs, L. %A Lörincz, A. %D 1994 %J Neural Computation %K learning, manifold networks neural %N 3 %P 441--458 %T Topology Learning Solved by Extended Objects: a Neural Network Model %V 6 %X It is shown that local, extended objects of a metrical topological space shape the receptive fields of competitive neurons to local filters. Self-organized topology learning is then solved with the help of Hebbian learning together with extended objects that provide unique information about neighborhood relations. A topographical map is deduced and is used to speed up further adaptation in a changing environment with the help of Kohonen type learning that teaches the neighbors of winning neurons as well.

@article{szepesvari1994d, abstract = {It is shown that local, extended objects of a metrical topological space shape the receptive fields of competitive neurons to local filters. Self-organized topology learning is then solved with the help of Hebbian learning together with extended objects that provide unique information about neighborhood relations. A topographical map is deduced and is used to speed up further adaptation in a changing environment with the help of Kohonen type learning that teaches the neighbors of winning neurons as well.}, added-at = {2020-03-17T03:03:01.000+0100}, author = {Szepesv{\'a}ri, {Cs}. and Bal{\'a}zs, L. and L{\"o}rincz, A.}, biburl = {https://www.bibsonomy.org/bibtex/255d42c0abfa2350eb41a77f32c88fe2f/csaba}, date-added = {2010-08-28 17:38:14 -0600}, date-modified = {2010-09-02 13:09:16 -0600}, interhash = {4008edd677cb2ab39f4749649f169af5}, intrahash = {55d42c0abfa2350eb41a77f32c88fe2f}, journal = {Neural Computation}, keywords = {learning, manifold networks neural}, number = 3, pages = {441--458}, pdf = {papers/toplearn94.ps.pdf}, timestamp = {2020-03-17T03:03:01.000+0100}, title = {Topology Learning Solved by Extended Objects: a Neural Network Model}, volume = 6, year = 1994 }