Theory Refinement using Hidden Nodes Connected from Relevant Input Nodes in Knowledge - based Artificial Neural Network


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 4, No. 11, pp. 2780-2785, Nov. 1997
10.3745/KIPSTE.1997.4.11.2780,   PDF Download:

Abstract

Although KBANN (knowledge-based artificial neural network) has been shown to be more effective than other machine learning algorithms, KBANN doesn't have the theory refinement capability because the topology of the network can't be altered dynamically. Although TopGen algorithm was proposed to extend the ability of KABNN in this respect, it also had some defects due to the connection of hidden nodes from all input nodes and the use of beam search. An algorithm, which could solve this TopGen's defects by adding the hidden nodes connected from only related input nodes and using hill-climbing search with backtracking, is proposed.


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]
S. D. Hee, "Theory Refinement using Hidden Nodes Connected from Relevant Input Nodes in Knowledge - based Artificial Neural Network," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 4, no. 11, pp. 2780-2785, 1997. DOI: 10.3745/KIPSTE.1997.4.11.2780.

[ACM Style]
Shim Dong Hee. 1997. Theory Refinement using Hidden Nodes Connected from Relevant Input Nodes in Knowledge - based Artificial Neural Network. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 4, 11, (1997), 2780-2785. DOI: 10.3745/KIPSTE.1997.4.11.2780.