The Brain & Neural Networks
Online ISSN : 1883-0455
Print ISSN : 1340-766X
ISSN-L : 1340-766X
Search
Advanced search
OR
Browse
Search
Volume 6, Issue 4
Displaying 1-11 of 11 articles from this issue
Show all abstracts
    • |<
    • <
    • 1
    • >
    • >|
  • Separate Extraction of Two Kind of Information by Self-Organizing-Overlapping-Map
    Masaoki Mitsutake, Kaoru Kida, Koji Wada, Koji Kurata
    1999 Volume 6 Issue 4 Pages 196-202
    Published: December 05, 1999
    Released on J-STAGE: January 17, 2011
    DOIhttps://doi.org/10.3902/jnns.6.196
    JOURNAL FREE ACCESS
    Show abstractHide abstract
    Self-organizing continuously-overlapping map is shown to have ability to detect the first and second nonlinear principal components. This is an extended version of the self-organizing overlapping mapping. The model was applied to FFT data of sound, and some others. These data are characterized by a combination of two kinds of features, such as the pitch and the quality of tone. The model has two self-organizing layers. One layer extracts and maps continuously one feature, and the other layer does the same with respect to the other feature. The ability of generalization depending on data structure is demonstrated. Comparison to Kohonen's SOM is also discussed.
    View full abstract
    Download PDF (506K)
  • A Modular-Type Neural Network with RBF Output Units
    Seiji Ishihara, Takashi Nagano
    1999 Volume 6 Issue 4 Pages 203-217
    Published: December 05, 1999
    Released on J-STAGE: January 17, 2011
    DOIhttps://doi.org/10.3902/jnns.6.203
    JOURNAL FREE ACCESS
    Show abstractHide abstract
    Recently, modular networks have been used to try to solve efficiently multiclass classification problems. However, the rejection rate on patterns of unlearned classes is usually very low. Moreover, when new classes are later added, old modules in the usual modular network need to be re-trained. A modular network proposed in this paper has RBF output units and an algorithm for incremental learning that improve these points. The results of computer simulations showed that the model achieved higher rejection rates on patterns of unlearned classes than the usual modular networks.
    View full abstract
    Download PDF (1313K)
    • |<
    • <
    • 1
    • >
    • >|
feedback
 Top