Theory Refinements in Knowledge-based Artificial Neural Networks by Adding Hidden Nodes


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 3, No. 7, pp. 1773-1780, Dec. 1996
10.3745/KIPSTE.1996.3.7.1773,   PDF Download:

Abstract

KBANN (knowledge-based artificial neural network) combining the symbolic approach and the numerical approach has been shown to be more effective than other machine learning models. However KBANN doesn''t have the theory refinement ability because the topology of network can''t be altered dynamically. Although TopGen was proposed to extend the ability of KABNN in this respect, it also had some defects due to the linking of hidden nodes to imput nodes and the use of beam search. The algorithm which could solve this TopGen''s defects, by adding the hidden nodes linked to next lower layer nodes and using hill-climbing search with backtracking, is designed.


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 Refinements in Knowledge-based Artificial Neural Networks by Adding Hidden Nodes," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 3, no. 7, pp. 1773-1780, 1996. DOI: 10.3745/KIPSTE.1996.3.7.1773.

[ACM Style]
Shim Dong Hee. 1996. Theory Refinements in Knowledge-based Artificial Neural Networks by Adding Hidden Nodes. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 3, 7, (1996), 1773-1780. DOI: 10.3745/KIPSTE.1996.3.7.1773.