Fast learning method for back-propagation neural network by evolutionary adaptation of learning rates

In training a back-propagation neural network, the learning speed of the network is greatly affected by its learning rate. None, however, has offered a deterministic method for selecting the optimal learning rate. Some researchers have tried to find the sub-optimal learning rates using various techn...

Full description

Saved in:
Bibliographic Details
Published in:Neurocomputing (Amsterdam) 1996, Vol.11 (1), p.101-106
Main Authors: Kim, Heung Bum, Jung, Sung Hoon, Kim, Tag Gon, Park, Kyu Ho
Format: Article
Language:English
Subjects:
Adaptive learning rates
Back-propagation neural network
Evolutionary programming
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In training a back-propagation neural network, the learning speed of the network is greatly affected by its learning rate. None, however, has offered a deterministic method for selecting the optimal learning rate. Some researchers have tried to find the sub-optimal learning rates using various techniques at each training step. This paper proposes a new method for selecting the sub-optimal learning rates by an evolutionary adaptation of learning rates for each layer at every training step. Simulation results show that the learning speed achieved by our method is superior to that of other adaptive selection methods.
ISSN:0925-2312
1872-8286
DOI:10.1016/0925-2312(96)00009-4