UNDERSTANDING THE PROBLEMS ASSOCIATED WITH ANALOG NEURAL INPUTS

G.A. Kohring
Additional contact information
G.A. Kohring: Zülpicher Straße 9 D-52349 Düren, Germany

International Journal of Modern Physics C (IJMPC), 1994, vol. 05, issue 02, 317-319

Abstract: Although it is generally agreed that neural networks with graded input neurons may correspond more closely with biological reality, there are some severe problems associated with such networks. When using multi-state neurons, it has recently been shown, that the information capacity falls off like1/Q2, if Q is the number of neuron states. Why this is so, will be discussed here along with a first-order solution to this problem. The solution lends itself quite naturally to implementation on a parallel computer.

Date: 1994
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0129183194000398
Access to full text is restricted to subscribers

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wsi:ijmpcx:v:05:y:1994:i:02:n:s0129183194000398

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0129183194000398

Access Statistics for this article

International Journal of Modern Physics C (IJMPC) is currently edited by H. J. Herrmann

More articles in International Journal of Modern Physics C (IJMPC) from World Scientific Publishing Co. Pte. Ltd.
Bibliographic data for series maintained by Tai Tone Lim ().