부산대학교 도서관

Koniocortex-Like Network model is a Bio-Inspired Neural Network structure that tries to replicate the architecture and properties of the biological koniocortex section of the brain. The structure is composed by different kinds of artificial neurons that interplay between them to create a competitive model that can be used to classify patterns. The classification performance obtained is based on different properties like lateral inhibition, metaplasticity and intrinsic plasticity, that allows a natural evolution of the network until obtaining the desired results. This kind of network has been applied to synthetic and real data showing big potential, now the network capabilities are tested using other state-of-the-art real data application: the classification of credit data from the Australian Credit Approval Database.