The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON SYSTEMS
Transactions ID Number: 28-424
Full Name: Ehsan Hossaini asl
Position: Student
Age: ON
Sex: Male
Address: unit.8,No.4,11th east aseman alley,sarv square,sadatabad,tehran,iran
Country: IRAN
Tel: 989123803259
Tel prefix:
Fax:
E-mail address: e.hossaini.asl@gmail.com
Other E-mails:
Title of the Paper: non uniform noisy data training using wavelet neural network based on modified sampling theory
Authors as they appear in the Paper: Ehsan Hossaini asl,Mehdi Shahbazian,Karim Salahshoor
Email addresses of all the authors: e.hossaini.asl@gmail.com,shahbazian_m@yahoo.com,salahshoor@yahoo.com
Number of paper pages: 11
Abstract: Global convergence and overfitting are the main problem in neural network training. One of the new methods to overcome these problems is sampling theory that is applied in training of wavelet neural network. In this paper this new method is improved for training of wavelet neural network in non uniform and noisy data. The improvements include suggesting a method for finding the appropriate feedback matrix, addition of early stopping and wavelet thresholding to training procedure. Two experiments are conducted for one and two dimensional function. The results establish a satisfied performance of this algorithm in reduction of generalization error, reduction the complexity of wavelet neural network and mainly avoiding overfitting.
Keywords: wavelet neural network; sampling theory; overfitting; early stopping; feedback matrix; wavelet thresholding; non uniform data
EXTENSION of the file: .pdf
Special (Invited) Session: Wavelet neural network based on sampling theory for non uniform noisy data
Organizer of the Session: 599-246
How Did you learn about congress:
IP ADDRESS: 87.107.118.19
