Dirbtinių neuroninių tinklų kolektyvų formavimo algoritmų kūrimas

• Main Author: Cibulskis, Vladas
• Other Authors: Maciulevičius, Stasys
• Format: Dissertation
• Language: Lithuanian
• Published: Lithuanian Academic Libraries Network (LABT) 2005
• Subjects: Informatics; Požymių atrinkimas; Neural network committees; Neigiamos koreliacijos mokymas; Negative correlation learning; Neuroninių tinklų kolektyvai; Neuroniniai tinklai; Feature selection; Neural network
• Online Access: http://vddb.library.lt/fedora/get/LT-eLABa-0001:E.02~2005~D_20050526_062729-44266/DS.005.0.01.ETD

Previous works on classification committees have shown that an efficient committee should consist of networks that are not only very accurate, but also diverse. In this work, aiming to explore trade-off between the diversity and accuracy of committee networks, the steps of neural network training, aggregation of the networks into a committee, and elimination of irrelevant input variables are integrated. To accomplish the elimination, an additional term to the Negative correlation learning error function, which forces input weights connected to the irrelevant input variables to decay, is added.