The Capacity of Core-Net ; Multi-Level 2-Layer Neural Networks


The Transactions of the Korea Information Processing Society (1994 ~ 2000), Vol. 6, No. 8, pp. 2098-2105, Aug. 1999
10.3745/KIPSTE.1999.6.8.2098,   PDF Download:

Abstract

One of the unsolved problems in Neural Networks is the interpretation of hidden layers. This paper defines the Core-Net which has an input(p levels) and an output(q levels) with 2-layers as a basic circuit of neural network. I have suggested an equation, ap,q = q^2/2p(p-1)-q/2(3p^2-7p 2) p^2-3p 2, which shows the capacity of the Core-Net and have proved it by using the mathematical induction. It has been also shown that some of the problems with hidden layers can be solved by using the Core-Net and using simulation of an example.


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]
P. J. Joon, "The Capacity of Core-Net ; Multi-Level 2-Layer Neural Networks," The Transactions of the Korea Information Processing Society (1994 ~ 2000), vol. 6, no. 8, pp. 2098-2105, 1999. DOI: 10.3745/KIPSTE.1999.6.8.2098.

[ACM Style]
Park Jong Joon. 1999. The Capacity of Core-Net ; Multi-Level 2-Layer Neural Networks. The Transactions of the Korea Information Processing Society (1994 ~ 2000), 6, 8, (1999), 2098-2105. DOI: 10.3745/KIPSTE.1999.6.8.2098.