Development of a multi-layer neural network for incomplete data set of environmental problems
Tadahiro Matubara, Tadayoshi Aoyama, Junko KAMBE, Umpei Nagashima, Hidenori Umeno · 2007
Multi-layer neural networks are used for the multi regression analysis of many kinds of phenomena whose expressions are unknown. The application fields are environmental problems and medicine designs. Where, we often find incomplete parts in descriptors, which make precision of the analysis be lower. Moreover, the incomplete parts make the linked parts of other descriptors be invalid. We often cannot calculate multi regression analysis, therefore, we wish to eliminate the wrong effects. In the paper, we discuss some approaches to eliminate the wrong effects, and derive a method on neural networks, which compensates defect descriptors. We call the method compensation quantitative structure-activity relationships method (CQSAR).