Dirbtinių neuroninių tinklų kolektyvų formavimo algoritmų kūrimas

Dirbtinių neuroninių tinklų kolektyvų formavimo algoritmų kūrimas

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, a...

Full description

Bibliographic Details
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
Description
Summary: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.

Similar Items