Abstract
A new neural network architecture is proposed and applied in classification of data from multiple sources. The new architecture is called a consensual neural network and its relation to hierarchical and ensemble neural networks is discussed. The consensual neural network architecture is based on statistical consensus theory and involves using non-linearly 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 the 0utputs 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. The performance of the consensual neur,al network archi.tecture is compared to that of a two-layer conjugate-gradient backpropagation neural network. The results with the proposed neural network architecture compare favourably to the backpropagation method in terms of classification accuracy.
Date of this Version
August 1991