Use of a quasi-Newton method in a feedforward neural network construction algorithm

1995 ◽  
Vol 6 (1) ◽  
pp. 273-277 ◽  
Author(s):  
R. Setiono ◽  
L.C.K. Hui
Keyword(s):  
Neural Network ◽  
Newton Method ◽  
Feedforward Neural Network ◽  
Network Construction ◽  
Construction Algorithm ◽  
Quasi Newton

Research on BP Neural Network Algorithm Based on Quasi-Newton Method

2014 ◽  
Vol 686 ◽  
pp. 388-394 ◽  
Author(s):  
Pei Xin Lu
Keyword(s):  
Neural Network ◽  
Empirical Analysis ◽  
Newton Method ◽  
Bp Neural Network ◽  
Bp Algorithm ◽  
Newton Methods ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Quasi Newton ◽  
Improved Bp Algorithm

With more and more researches about improving BP algorithm, there are more improvement methods. The paper researches two improvement algorithms based on quasi-Newton method, DFP algorithm and L-BFGS algorithm. After fully analyzing the features of quasi-Newton methods, the paper improves BP neural network algorithm. And the adjustment is made for the problems in the improvement process. The paper makes empirical analysis and proves the effectiveness of BP neural network algorithm based on quasi-Newton method. The improved algorithms are compared with the traditional BP algorithm, which indicates that the improved BP algorithm is better.

Quasi-Newton Method for DSPSL Bandpass Filter Design

2011 ◽  
Vol 219-220 ◽  
pp. 778-781
Author(s):  
Shan Wang
Keyword(s):  
Neural Network ◽  
Newton Method ◽  
Bandpass Filter ◽  
Filter Design ◽  
Nonlinear Circuits ◽  
Analysis Techniques ◽  
The Neural Network ◽  
Electro Magnetic ◽  
Quasi Newton ◽  
Good Agreement

A method based on neural-network is developed and applied to analyze the DSPSL filter design. Through the neural network analysis of nonlinear circuits, it can enhance the efficiency of electro-magnetic (EM) analysis techniques for DSPSL filter design. Quasi-Newton method is adopted, which has shorter training period and the faster convergence. A good agreement between ANN results and EM simulations verifies the validity of this proposed MLPNN model.

Sign in / Sign up

Export Citation Format

Share Document