DSpace

Future University Hakodate Academic Archive >
Faculty and Students >
Dept. of Media Architecture >
Pitoyo, Hartono >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10445/5285

Title: Learning Initialized by Topologically Correct Map
Authors: Hartono, Pitoyo
Trappenberg, Thomas
Abstract: In this research, we proposed a model of hierarchical three-layered perceptron, in which the middle layer contains a two dimensional map where the topological relationship of the high dimensional input data (external world) are internally representated. The proposed model executes a two-phase learning algorithm, such taht a supervised learning is proceded by a self-organization unsupervised learning. The objective of this study is to build a simple neural network model (which is more biologicaly realistic than the standard Multilayer Perceptron model), that can form an internal representation that supports its learning potential.
Research Achievement Classification: 国際会議/International Conference
Type: Conference Paper
Peer Review: あり/yes
Solo/Joint Author(s): 共著/joint
Published journal or presented
academic conference: 
Proc. IEEE Int. Conf. on Systems, Man and Cybernetics (SMC 2009)
Spage: 2802
Epage: 2806
Date: 2009
Publisher: IEEE
Appears in Collections:Pitoyo, Hartono

Files in This Item:

There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Copyright © 2010-2012 FUTURE UNIVERSITY HAKODATE.
DSpace Software Copyright © 2002-2010  Duraspace