G.A. Carpenter and S. Grossberg, "ART2: Self-Organizing of Stable Category Recognition Codes for Analog Input Patterns," Applied Optics, Vol. 26, No. 23, pp. 4919-4930, 1987.  Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Cascade Fuzzy Adaptive Hamming Net: A Coarse-to-Fine.. - Hong-Yuan Mark Liao (Correct)
....of forgetting previously learned categories if the environment changes. Usually, an unknown input scene is very complex and may exhibit a hierarchical structure [5 7] If input data contain structural relationships, a single layer of output nodes in traditional self organizing neural networks [1,2,4,8] is definitely not sufficient to reveal their hierarchical characteristics. In order to make the scheme more flexible and powerful, Bartfai proposed a Hierarchical ART (HART) 6] that is capable of developing hierarchical class representation through self organization of input patterns. However, ....
G. A. Carpenter and S. Grossberg, "ART2: Self-Organizing of Stable Category Recognition Codes for Analog Input Patterns", Applied Optics, vol. 26, no. 23, pp. 4919--4930, Dec. 1987.
CFART: A New Multi-Resolutional Adaptive Resonance.. - Liao, Hung, Sze.. (Correct)
....serious problem associated with this scheme is that the number of categories the network can allocate for a given training set is restricted by the number of output nodes. An example reflecting this problem is the Self Organizing Feature Map [12] The Adaptive Resonance Theory (ART) neural network [7, 8, 11], on the other hand, can create a new node in response to new data during the training stage as well as during the recalling stage. A series of ART type unsupervised learning networks [5, 13 17] has been developed and successfully applied to many applications. Some salient characteristics of ....
G. A. Carpenter and S. Grossberg, "ART2: Self-Organizing of Stable Category Recognition Codes for Analog Input Patterns", Applied Optics, vol. 26, no. 23, pp. 4919--4930, Dec. 1987.
Supervised Competitive Learning - Fuller, Jr., Kimura (1994) (Correct)
....controlled by the vigilance parameter. An ART system with low vigilance will permit grouping of patterns that are only grossly similar, and a system with high vigilance will try to form separate categories for patterns that have only minor differences. In the ART2 BP network, Sorheim uses the ART2 [Carpenter and Grossberg 1987] model to build a supervised backpropagation network in his attempt to resolve the stability plasticity dilemma [Sorheim 1991] A simple backpropagation net is connected to each output unit of the ART2 subsystem. The competitive learning occurs in the ART2 subsystem, and no competition exists ....
Carpenter, G. A. and Grossberg, S. (1987). ART2: Self-Organizing of Stable Category Recognition Codes for Analog Input Patterns. Applied Optics, 4919-4930.
Neural Networks for Modelling Applications Neural Networks for.. - Petriu (Correct)
No context found.
G.A. Carpenter and S. Grossberg, "ART2: Self-Organizing of Stable Category Recognition Codes for Analog Input Patterns," Applied Optics, Vol. 26, No. 23, pp. 4919-4930, 1987.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC