Title :
A first order adaptive learning rate algorithm for backpropagation networks
Author :
Nachtsheim, Philip R.
Author_Institution :
Inf. Sci. Div., NASA Ames Res. Center, Moffett Field, CA, USA
fDate :
27 Jun-2 Jul 1994
Abstract :
A simple method for determining the learning rate parameter of the backpropagation algorithm is described and analyzed. The learning rate parameter is determined at each step of the iteration by attempting to find a double root of the quadratic cost function. This is opposed to the traditional approach of viewing learning as an optimization problem. It is shown that this method of determining the learning rate parameter leads to accelerated convergence for several benchmark cases
Keywords :
backpropagation; convergence; neural nets; accelerated convergence; backpropagation networks; double root; first order adaptive learning rate algorithm; learning rate parameter; quadratic cost function; Acceleration; Algorithm design and analysis; Backpropagation algorithms; Convergence; Cost function; Information analysis; NASA;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.374171
