A consensual neural networkA neural network architecture called a consensual neural network (CNN) is proposed for the classification of data from multiple sources. Its relation to hierarchical and ensemble neural networks is discussed. CNN is based on the statistical consensus theory and uses nonlinearly transformed input data. The input data are transformed several times, and the different transformed data are applied as if they were independent inputs. The independent inputs are classified using stage neural networks and outputs from the stage networks are then weighted and combined to make a decision. Experimental results based on remote-sensing data and geographic data are given.
Document ID
19920052673
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Benediktsson, J. A. (NASA Headquarters Washington, DC United States)
Ersoy, O. K. (NASA Headquarters Washington, DC United States)
Swain, P. H. (Purdue University West Lafayette, IN, United States)
Date Acquired
August 15, 2013
Publication Date
January 1, 1991
Subject Category
Cybernetics
Meeting Information
Meeting: IGARSS ''91: Annual International Geoscience and Remote Sensing Symposium