A.Ultsch and D.Korus. Integration of neural networks with knowledge-based systems. In Proc. IEEE Int.Conf.Neural Networks, Perth, 1995. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Adaptive hierarchical cluster analysis by Self-Organizing Box .. - Galliat, Deuflhard (2000) (1 citation) (Correct)
....a clustering of the whole input space, too. Although it is possible to use a partitioning or hierarchical cluster algorithm for this task, this is not 16 the usual way, because in this case it is better to use them directly. Instead one traditionally uses methods, like the u matrix method [1], that visualize the di erences of the codebook vectors on the map. Together with additional visualization tools [5] they allow the human expert to identify clusters on the map and therefore in the whole input space. Although these cluster methods do neither need the number of clusters as an ....
A.Ultsch and D.Korus. Integration of neural networks with knowledge-based systems. In Proc. IEEE Int.Conf.Neural Networks, Perth, 1995.
Clustering Data of Different Information Levels - Galliat (1999) (Correct)
....A typical object has for only 10 20 of these attributes a value greater than zero. The zero value represents the missing of the related code. Our task is to cluster the almost 30000 objects, using the Self Organizing Map (SOM) algorithm [5, 3] in combination with u matrix visualization [1]. We will show the results of the following four di erent approaches: 1. Use the Euclidean distance based on the 36 attributes. 2. Use the euclidian distance based on the 36 attributes, but with the zero values as missing values, i.e. the zeros are not used for the distance computing and the ....
A.Ultsch and D.Korus. Integration of neural networks with knowledge-based systems. In Proc. IEEE Int.Conf.Neural Networks, Perth, 1995.
Self-Organizing Maps Combined with Eigenmode Analysis.. - Galliat, Huisinga.. (1999) (Correct)
....an interpretation of SOMs as topographic maps of the multi dimensional data space, b) it permits to include additional data into the treatment during the course of computation [9] An important eld of application of SOMs is Data Mining, especially cluster analysis therein. By using the u matrix [1] or any other visualization techniques [8] any well trained analyst will easily identify clusters on a heuristic basis. Di erent experts will need di erent computation times and will come up with di erent results which gives the whole method an undesirable avour of personal bias. This is a ....
A.Ultsch and D.Korus. Integration of neural networks with knowledge-based systems. In Proc. IEEE Int.Conf.Neural Networks, Perth, 1995.
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