Neural network structure. The input into this network is a vector , which consists of s1, s2, and s3, representing the similarity in name, properties, and ancestors, respectively, for a given pair of concepts. wi are weights assigned to each input. The output from this network is s, the similarity value between these two concepts as given by Formula 3.
Huang et al. BMC Genomics 2008 9(Suppl 2):S16 doi:10.1186/1471-2164-9-S2-S16