|
|
|
|
|
Mojtaba Nayyeri, Modjtaba Rouhani, Hadi Sadoghi Yazdi, Marko M. Mäkelä, Alaleh Maskooki and Yury Nikulin
One of the main disadvantages of the traditional mean square error (MSE)-based constructive networks is their poor performance in the presence of non-Gaussian noises. In this paper, we propose a new incremental constructive network based on the correntro...
ver más
|
|
|
|
|
|
|
|
|
|
|
Napsu Karmitsa, Sona Taheri, Kaisa Joki, Pauliina Paasivirta, Adil M. Bagirov and Marko M. Mäkelä
In this paper, a new nonsmooth optimization-based algorithm for solving large-scale regression problems is introduced. The regression problem is modeled as fully-connected feedforward neural networks with one hidden layer, piecewise linear activation, an...
ver más
|
|
|
|
|
|
|
|
|
|
|
Soha Abd El-Moamen Mohamed, Marghany Hassan Mohamed and Mohammed F. Farghally
In this paper, a proposed algorithm that dynamically changes the neural network structure is presented. The structure is changed based on some features in the cascade correlation algorithm. Cascade correlation is an important algorithm that is used to so...
ver más
|
|
|
|
|
|
|
|
|
|
|
Ma, L. Khorasani, K.
Pág. 1112 - 1126
|
|
|
|
|
|
|
|
|
|
|
Jin, X; Srinivasan, D; Cheu, R L
Pág. 1173 - 1187
|
|
|
|
|
|
|
|
|
|
|
Kwok, T-Y; Yeung, D-Y
Pág. 630 - 645
|
|
|
|
|
|
|
|
|
|
|
Kwok, T-Y; Yeung, D-Y
Pág. 1131 - 1148
|
|
|
|
|
|