Preprocessing for informative, ecient andsmall networks
2001 (English)In: Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference (Vol 3), IEEE Computer Society, 2001, 1776-1779 p.Conference paper (Refereed)
We demonstrate how sigmoidal fuzzification affects discriminant capacities. In particular, we study thepreprocessing perceptron and compare it with the multilayer perceptron. Case studies are selected from the medical domain, where output performance needs to be related to requirements for high sensitivities. These smaller and more informative networks tend also to be more robust with respect to accuracy with various requirements on sensitivities
Place, publisher, year, edition, pages
IEEE Computer Society, 2001. 1776-1779 p.
IdentifiersURN: urn:nbn:se:umu:diva-80605DOI: 10.1109/NAFIPS.2001.943821ISBN: 0-7803-7078-3OAI: oai:DiVA.org:umu-80605DiVA: diva2:650503
Joint 9th IFSA World Congress and 20th NAFIPS International Conference, 25-28 July 2001, Vancouver, BC