000004596 001__ 4596
000004596 005__ 20141119144537.0
000004596 04107 $$aeng
000004596 046__ $$k2002-06-02
000004596 100__ $$aAvazdavani, Ardavan
000004596 24500 $$aAPPLICATION OF MODIFIED ART2 ARTIFICIAL NEURAL NETWORK IN CLASSIFICATION OF STRUCTURAL MEMBERS

000004596 24630 $$n15.$$pProceedings of the 15th ASCE Engineering Mechanics Division Conference
000004596 260__ $$bColumbia University in the City of New York
000004596 506__ $$arestricted
000004596 520__ $$2eng$$aIn this research the basic algorithm of ART2 neural network has been modified for proper and efficient classification of vectors. In the basic architecture of ART2, the length of vectors is neglected. This causes error in sorting; parallel vectors with different length are classified in the same category. To overcome this deficiency, an input virtual neuron is added to consider vector length. The modified architecture not only considers the similarity of vectors direction but also considers the magnitude of vectors in sorting. ART neural networks are classified as unsupervised learning nets, a method is presented for supervised learning of ART2 without general changes in the basic algorithm.

000004596 540__ $$aText je chráněný podle autorského zákona č. 121/2000 Sb.
000004596 653__ $$aArtificial Neural Network, Adaptive Resonance Theory, ART2, Structural design

000004596 7112_ $$a15th ASCE Engineering Mechanics Division Conference$$cNew York (US)$$d2002-06-02 / 2002-06-05$$gEM2002
000004596 720__ $$aAvazdavani, Ardavan$$iMortazavi, Seyed S.
000004596 8560_ $$ffischerc@itam.cas.cz
000004596 8564_ $$s169117$$uhttps://invenio.itam.cas.cz/record/4596/files/009.pdf$$yOriginal version of the author's contribution as presented on CD, .
000004596 962__ $$r4594
000004596 980__ $$aPAPER