Modification of the Mean-Square Error Principle to Double the Convergence Speed of a Special Case of Hopfield Neural Network Used to Segment Pathological Liver Color Images
- Topics:
- Healthcare Services
- Tags:
- BioMed Central,
- Error
- Source:
- BioMed Central
FREE Registration is required
Overview: This paper analyzes the effect of the mean-square error principle on the optimization process using a Special Case of Hopfield Neural Network (SCHNN). The segmentation of multidimensional medical and color images can be formulated as an energy function composed of two terms: the sum of squared errors, and a noise term used to avoid the network to be stacked in early local minimum points of the energy landscape. The findings show that the sum of weighted error, higher than simple squared error, leads the SCHNN classifier to reach faster a local minimum closer to the global minimum with the assurance of acceptable segmentation results.
(Is this item miscategorized? Does it need more tags? Let us know.)
Format: PDF | Size: 1,669KB | Date: Dec 2004 | Pages: 13
