AN EFFICIENT MULTI-SPIN CODING ALGORITHM FOR NEURAL NETWORKS

Martin Neschen
Additional contact information
Martin Neschen: Institut für Theoretische Physik der Universität zu Köln, Zülpicher Straße 77, D-5000 Köln 41, Germany

International Journal of Modern Physics C (IJMPC), 1991, vol. 02, issue 02, 623-636

Abstract: A new method for large-scale numerical simulations of neural networks is proposed which reduces the computational effort by incrementally updating the local fields and thus restricting the operations to flipped spins only. A highly optimized multi-spin algorithm is described employing words oriented along the columns of the coupling matrix unlike the horizontal structure in existing high-speed algorithms. An effective rate of35*109couplings/s on a Cray-YMP can be attained which is about five times as fast as best existing multi-spin implementations.

Keywords: Neural Networks; Multi-Spin Coding; Computer Algorithms; Large-Scale Simulations (search for similar items in EconPapers)
Date: 1991
References: Add references at CitEc
Citations:

Downloads: (external link)
http://www.worldscientific.com/doi/abs/10.1142/S0129183191000925
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:02:y:1991:i:02:n:s0129183191000925

Ordering information: This journal article can be ordered from

DOI: 10.1142/S0129183191000925

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 ().