Author： Kavzoglu T. Mather P. M.
Publisher： Taylor & Francis Ltd
ISSN： 1366-5901
Source： International Journal of Remote Sensing, Vol.20, Iss.14, 1999-09, pp. : 2787-2803
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
The use of three techniques for pruning artificial neural networks (magnitude-based pruning, optimum brain damage and optimal brain surgeon) is investigated, using microwave SAR and optical SPOT data to classify land cover in a test area located in eastern England. Results show that it is possible to reduce network size significantly without compromising overall classification accuracy; indeed, accuracy may rise as the number of links decreases. However, individual class accuracies and the spatial distribution of the pixels forming the individual classes may change significantly. If the network is pruned too severely some classes may be eliminated altogether. In terms of maintaining overall classification accuracy the optimal brain surgeon algorithm gave the best results, and magnitude-based pruning also gave good results despite its simplicity. The optimum brain damage algorithm performed least well of the three methods tested.
Related content
Access to resources
Recommend
By Murthy C. S. Raju P. V. Badrinath K. V. S.
International Journal of Remote Sensing, Vol. 24, Iss. 23, 2003-12 ,pp. :