For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Self-Organizing Relationship (SOR) Network
Takeshi YAMAKAWA Keiichi HORIO
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1999/08/25
Print ISSN: 0916-8508
Type of Manuscript: LETTER
Category: Neural Networks
self-organizing, I/O relationship, evaluation, attraction, repulsion,
Full Text: PDF>>
In this letter, the novel mapping network named self-organizing relationship (SOR) network, which can approximate the desired I/O relationship by employing the modified Kohonen's learning law, is proposed. In the modified Kohonen's learning law, the weight vectors are updated to be attracted to or repulsed from the input vector.