Fast Conjugate Gradient Algorithm for Feedforward Neural Networks

Author(s):  
Jarosław Bilski ◽  
Jacek Smoląg
2019 ◽  
Vol 24 (1) ◽  
pp. 115
Author(s):  
Hind H. Mohammed

In this paper, we will present different type of CG algorithms depending on Peary conjugacy condition. The new conjugate gradient training (GDY) algorithm using to train MFNNs and prove it's descent property and global convergence for it and then we tested the behavior of this algorithm in the training of artificial neural networks and compared it with known algorithms in this field through two types of issues   http://dx.doi.org/10.25130/tjps.24.2019.020


Sign in / Sign up

Export Citation Format

Share Document