45.

[Cover] [Contents] [Index]

Page 138

Figure 3.18 (a) An overview of a fuzzy ARTMAP architecture containing two fuzzy ART systems, (b) The map field is connected to F2b with 1-to-1, non-adaptive pathways in both directions. Each F2a neurone is connected to all map field Fab nodes via adaptive weights. See text for further explanation.

desired category for the current data feature presented to ARTa. The map field Fab is used to form predictive associations between categories and match tracking (defined below). The number of neurones in Fab is equal to the number of desired classes. Let variables in ARTa and ARTb be desig

[Cover] [Contents] [Index]


Classification Methods for Remotely Sensed Data
Classification Methods for Remotely Sensed Data, Second Edition
ISBN: 1420090720
EAN: 2147483647
Year: 2001
Pages: 354

flylib.com © 2008-2017.
If you may any questions please contact us: flylib@qtcs.net