Improved learning method of Discrete Recurrent Neural Network inferring Regular Grammars


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 6, No. 12, pp. 3569-3572, Dec. 1999
10.3745/KIPSTE.1999.6.12.3569,   PDF Download:

Abstract

In this paper, we describe two considerations that improve the learning performance of Discrete Second-Order Recurrent Neural Network(DRNN) inferring regular grammars. One is due to the viewpoint of training patterns which are inputs of DRNN. It is to investigate learing performances according to a variety of input order and describe the best modify algorithm in order to reduce total learning time. We suggest the modified learning method and show the improved result of experiments.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from September 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article
[IEEE Style]
H. K. Jung and S. H. Jung, "Improved learning method of Discrete Recurrent Neural Network inferring Regular Grammars," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 6, no. 12, pp. 3569-3572, 1999. DOI: 10.3745/KIPSTE.1999.6.12.3569.

[ACM Style]
Hyeon Ki Jung and Soon Ho Jung. 1999. Improved learning method of Discrete Recurrent Neural Network inferring Regular Grammars. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 6, 12, (1999), 3569-3572. DOI: 10.3745/KIPSTE.1999.6.12.3569.