Improvement in the learning process as a function of distribution characteristics of binary data set
Küçük Resim Yok
Tarih
2000
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
IEEE, Piscataway, NJ, United States
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
In literature improvements in neural learning are reported on, which have been achieved through input data manipulation, based on entirely experimental studies. Theoretical background is not supplied for these studies and neural networks are employed as a 'black box' model. Within this work, this problem is highlighted and the impact of the modified training sets is evaluated in order to establish a theoretical background for the phenomenon. For this end, a number of binary training data is employed to show how does the learning process depend on data distribution within the training sets.
Açıklama
IEEE
10th Mediterranean Electrotechnical Conference (MALECON2000) -- 29 May 2000 through 31 May 2000 -- Lemesos, Cyprus -- 57862
10th Mediterranean Electrotechnical Conference (MALECON2000) -- 29 May 2000 through 31 May 2000 -- Lemesos, Cyprus -- 57862
Anahtar Kelimeler
Kaynak
Proceedings of the Mediterranean Electrotechnical Conference - MELECON
WoS Q Değeri
N/A
Scopus Q Değeri
N/A
Cilt
2
