Carpenter, G. A., Grossberg, S., and Rosen, D. B., "Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system", Neural Networks, Vol. 4, pp. 759-771, 1991a.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....Vector Machines (SVM) 9] and Associative Resonance Associative Map (ARAM) 10] for Chinese text categorization. kNN and SVM have been reported as the top performing methods for English text categorization [7] ARAM belongs to a popularly known family of predictive selforganizing neural networks [11] but until recently, has not been used for text categorization. Our comparative experiments employed two Chinese corpora, namely the TREC People s Daily news corpus (TREC) and the Chinese web corpus (WEB) Based on the benchmark experiments on these two corpora, we examined and compared the ....

....the decomposition idea of Osuna et al. 14] has been proven to be practical in learning from relatively high dimensional and large scale training set [15] 3.3. Adaptive Resonance Associative Map Adaptive Resonance Associative Map (ARAM) is a class of predictive self organizing neural networks [11] that performs incremental supervised learning of recognition categories (pattern classes) and multidimensional maps of patterns. An ARAM system can be visualized as two overlapping Adaptive Resonance y F1 a 2 F a ART b ART AB Feature field Feature field Category field ....

[Article contains additional citation context not shown here]

G.A. Carpenter, S. Grossberg, and D.B. Rosen, "Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system," Neural Networks, vol. 4, pp. 759-- 771, 1991.

....candidate features, such as RC [26] or genetic algorithms. The core of our classification, i.e. the system based on the FasArt neuro fuzzy architecture, is described briefly in section 4. Such an architecture, motivated by studies on human cognition that resulted in the original ART architectures [9][7] is consistent with our general approach based on human modeling. Furthermore, its compliance to the plasticity stability dilemma [13] its formulation as a fuzzy logic system, and our previous experience on similar architectures [11] contributed to the adoption of this specific classification ....

.... on one hand heuristic methods usually based on ideas coming from statistical classification [1] on the other, embedding of fuzzy logic into neural networks in order to have fuzzy systems with learning capabilities [15] Within the architectures of Adaptive Resonance Theory, the Fuzzy ART model [9] introduces fuzzy operators. Thus, a classifying module was achieved, that pretends to provide a self organizing classification, based on categories of fuzzy nature. Similarly, a supervised architecture, Fuzzy ARTMAP [7] is built using Fuzzy ART modules within the original ARTMAP architecture ....

[Article contains additional citation context not shown here]

G.A. Carpenter, S.Grossberg, and D.B. Rosen, "Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance systems", Neural Networks, 4(1):759-771, 1991.

....a generalization of binary ARTMAP [4] learns to classify inputs by a pattern of fuzzy membership values between 0 and 1 indicating the extent to which each feature is present. This generalization is accomplished by replacing the ART 1 modules [2] of the binary ARTMAP system with fuzzy ART modules [5]. Each ARTMAP system includes a pair of Adaptive Resonance Theory modules (ART a and ART b ) that create stable recognition categories in response to arbitrary sequences of input patterns (Figure 3) An associative learning network and an internal controller link these modules to make the ARTMAP ....

....Theory modules (ART a and ART b ) that create stable recognition categories in response to arbitrary sequences of input patterns (Figure 3) An associative learning network and an internal controller link these modules to make the ARTMAP system operate in real time. 2. 1 Fuzzy ART Fuzzy ART [5] incorporates computations from fuzzy set theory into ART systems. By replacing the crisp (nonfuzzy) intersection operator ( that describes ART 1 dynamics [2] by the fuzzy AND operator ( of fuzzy set theory,fuzzyART can learn stable categories in response to either analog or binary patterns. ....

G. A. Carpenter, S. Grossberg, and D. B. Rosen. Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Networks, 4:759--771, 1991.

....(ART) that performs incremental supervised learning of recognition categories (pattern classes) and multidimensional maps of patterns. An ARAM can be visualized as two overlapping ART [4] modules consisting of two input fields b a F F 1 1 and with an F 2 category field (Figure 5) Fuzzy ART [5] is used here. Figure 5. ARAM Architecture For each document d, an information vector A = a 1 , a 2 , a M ) is derived such that a i = 1 tf(w ) idf (w i ) where the term frequency tf(w i ) is the number of times the keyword w i appears in document d and the inverse document ....

Carpenter, G. A., Grossberg, S., and Rosen, D.B. Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Networks, 4 (1991), 759-771.

....are with the Department of System Engineering and Automatic Control, Polytechnical University of Cartagena, Murcia, Spain. Publisher Item Identifier S 1045 9227(02)00347 8. datasets typically cause Fuzzy ARTMAP to generate too many rules [7] This problem is known as category proliferation [8]. It is due to the application of the match tracking mechanism, that however is necessary to guarantee fast, accurate, on line learning. This mechanism is fired after a pattern has been presented, if the selected category in ART predicts a wrong label: vigilance is raised and a finer or new ....

....recognition. Finally Section VI draws the main conclusions and outlines future research tasks. II. FUZZY ARTMAP Fuzzy ARTMAP [6] is the most popular architecture derived from ART. It is capable of performing fast, stable learning in a supervised setting. In includes two unsupervised Fuzzy ART [8] modules, that partition the input and output spaces; however, fuzzy ARTMAP may suffer from category proliferation [8] 10] This section reviews the architecture and dynamics of Fuzzy ARTMAP and thus serves as a basis for Boosted ARTMAP [12] and ARTMAP, the proposed architecture. Emphasis will ....

[Article contains additional citation context not shown here]

G. A. Carpenter, S. Grossberg, and D. B. Rosen, "Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system," Neural Networks, vol. 4, no. 1, pp. 759--771, 1991.

....This paper proposes an organizational network for dynamic partnership in a dynamic environment with adaptive ability, learning ability, competitive ability. It is based on Fuzzy Adaptive Resonance Theory (Fuzzy ART) that is a neural network model and is proposed by Carpenter, Grossberg, and Rosen[5] for clustering binary or analog data. The ART network is a self organizational network and is based on a winner takes all competitive principle. It has unsupervised learning ability and adaptive ability for data clustering. In this paper, each actor involved in product configuration management ....

Carpenter G.A., Grossberg S., Rosen D.B.: Fuzzy ART: Fast Stable Learning and Categorization of Analog Pattern by an Adaptive Resonance System. Neural Networks 4(6) (1991) 759-771

....F1 a r b r 2 F a ART b ART A B Feature field Feature field Category field Fig. 2. The Adaptive Resonance Associative Map architecture The ART modules used in ARAM can be ART 1 [3] which categorizes binary patterns, or analog ART modules such as ART 2 [4] ART 2 A [5] and fuzzy ART [6][14] which categorize both binary and analog patterns. The ARAM 2 A algorithm based on ART 2 A is introduced below. Parameters: ARAM 2 A dynamics are determined by the learning rates # a [0, 1] the vigilance parameters # a [0, 1] the contribution parameter # [0, 1] and the k max ....

G.A. Carpenter, S. Grossberg, and D.B. Rosen. Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Networks, 4:759-771, 1991.

.... as two overlapping Adaptive Resonance Theory (ART) 1] modules consisting of two input fields F 1 and F 1 with an F 2 category field (Figure 4) The ART modules used in ARAM can be ART 1 [1] which categorizes binary patterns, or analog ART modules such as ART 2, ART 2 A, and fuzzy ART [2] which categorize both binary and analog patterns. Fuzzy ARAM [7] 8] that is based on fuzzy ART is used in FOCI. For User Configurable Clustering, the F 1 field contains the activities of the information vectors and the F 1 field contains the activities of the preference vectors. ....

G. A. Carpenter, S. Grossberg, and D. B. Rosen. Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Networks, 4:759--771, 1991.

....of parameters. As mentioned previously, this choice of the network parameters leads to Fuzzy ARTMAP network architectures of minimum size. The functionality of Fuzzy ARTMAP is better illustrated by referring to the geometrical interpretation of the weights in ART a . As initially discussed in [6] and further elaborated in [7] every weight vector in ART a defines a hyperrectangle (hyperbox) in the input pattern space that includes all patterns that chose this weight vector as their representative during the training process. In Figure 2, we show the hyperrectangle that the weight vector ....

G. A. Carpenter, S. Grossberg, and D. B. Rosen, "Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system," Neural Networks, Vol. 4, pp. 759-771, 1991.

....on line visual learning method for color image segmentation and object tracking in dynamic environment. Such on line visual learning method is indispensable for realizing a vision based system which can keep running in real world. To realize on line learning, our method utilizes fuzzy ART model [4] which is a kind of neural network for competitive learning. Although color image we deal with is represented by YUV color space, YUV space is not suitable for inputs of fuzzy ART model. For this reason, YUV space is transformed to a certain color space. This transformation enables fuzzy ART model ....

....in [2] Color models at time t = k is estimated by updating color models at time t = k 1 based on color information in the target regions at time t = k. In the following subsection, first, we explain fuzzy ART system which is main part of our learning system according to the literature [4]. Next, we present how to transform YUV signal into Yr# signal. Finally, we show how to update the spatial model of the tracked target. 2.1 On line learning system based on Fuzzy ART model A fuzzy ART model consists of three fields F 0 , F 1 and F 2 . In the field F 0 , a current input vector is ....

[Article contains additional citation context not shown here]

G. A. Carpenter, S. Grossberg, and D. B. Rosen. "Fuzzy ART: Fast Stable Learning and Categorization of Analog Patterns by an Adaptive Resonance System". Neural Networks., 4:759--771, 1991.

No context found.

Carpenter, G. A., Grossberg, S., and Rosen, D. B., "Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system", Neural Networks, Vol. 4, pp. 759-771, 1991a.

No context found.

G.A. Carpenter, S. Grossberg, and D.B. Rosen, Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system, Neural Z. Networks 4 1991 , 759#771.

No context found.

G. A. Carpenter, S. Grossberg, and D. B. Rosen, "Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system," Neural Networks, vol. 4, pp. 759--771, 1991.

No context found.

G.A. Carpenter, S. Grossberg, and D.B. Rosen, Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system, Neural Z. Networks 4 1991 , 759#771.

No context found.

G.A. Carpenter, S. Grossberg and D.B. Rosen. "Fuzzy art: Fast stable learning and categorization of analog patterns by an adaptive resonance system". Neural Networks, 4:759-771, 1991.

No context found.

Carpenter, G. A., Grossberg, S., and Rosen, D. B. (1991), Fuzzy ART : Fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Networks, 4, 759-771.

No context found.

G.A. Carpenter, S. Grossberg, and D.B. Rosen, Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system, Neural Z. Networks 4 1991 , 759#771.

No context found.

Carpenter, G.A., Grossberg, S., & Rosen, D. B. (1991). Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Networks, 4, 759-771.

No context found.

G.A. Carpenter, S. Grossberg, and D.B. Rosen, Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system, Neural Networks, 4, 759-771, 1991.

No context found.

G. Carpenter, S. Grossberg, and D. B. Rosen, "Fuzzy art: Fast stable learning and categorization of analog patterns by an adaptive resonance system," Neural Networks, vol. 4, pp. 759--771, 1991. 19

No context found.

Carpenter, G.A., S. Grossberg, and D.B. Rosen. 1991. "Fuzzy art: Fast stable learning and categorization of analog patterns by an adaptive resonance system". Neural Networks, 4:759--771.

No context found.

G. A. Carpenter, S. Grossberg and D. B. Rosen, \Fuzzy ART: Fast Stable Learning and Categorization of Analog Patterns by an Adaptive Resonance System", Neural Networks, Vol. 4, No. 6, pp. 759-771, 1991.

No context found.

G.A. Carpenter, S. Grossberg, and D.B. Rosen, "Fuzzy ART: Fast Stable Learning and Categorization of Analog Patterns by an Adaptive Resonance System," Neural Networks, vol. 4, no. 6, pp. 759-771, 1991.

No context found.

G.A. Carpenter, S. Grossberg, and D.B. Rosen. Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Networks, 4:759-771, 1991.

No context found.

G. A. Carpenter, S. Grossberg, and D. B. Rosen. 1991. Fuzzy ART: fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Networks, 4:759--771.

First 50 documents  Next 50

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