DocumentCode :
3661141
Title :
Quasi-Newton learning methods for complex-valued neural networks
Author :
Călin-Adrian Popa
Author_Institution :
Department of Computer and Software Engineering, Polytechnic University Timiş
fYear :
2015
fDate :
7/1/2015 12:00:00 AM
Firstpage :
1
Lastpage :
8
Abstract :
This paper presents the full deduction of the quasi-Newton learning methods for complex-valued feedforward neural networks. Since these algorithms yielded better training results for the real-valued case, an extension to the complex-valued case is a natural option to enhance the performance of the complex backpropagation algorithm. The training methods are exemplified on various well-known synthetic and real-world applications. Experimental results show a significant improvement over the complex gradient descent algorithm.
Keywords :
Open systems
Publisher :
ieee
Conference_Titel :
Neural Networks (IJCNN), 2015 International Joint Conference on
Electronic_ISBN :
2161-4407
Type :
conf
DOI :
10.1109/IJCNN.2015.7280450
Filename :
7280450
Link To Document :
بازگشت