A modified back-propagation method to avoid false local minima.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 12662775.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
The back-propagation method encounters two problems in practice, i.e., slow learning progress and convergence to a false local minimum. The present study addresses the latter problem and proposes a modified back-propagation method. The basic idea of the method is to keep the sigmoid derivative relatively large while some of the error signals are large. For this purpose, each connecting weight in a network is multiplied by a factor in the range of (0,1], at a constant interval during a learning process. Results of numerical experiments substantiate the validity of the method.