Content-based information retrieval using an embedded neural associative memory
Schmidt M, Rückert U (2001)
In: Parallel and Distributed Processing, 2001. Proceedings. Ninth Euromicro Workshop on. IEEE Comput. Soc: 443-450.
Konferenzbeitrag
| Veröffentlicht | Englisch
Download
Es wurden keine Dateien hochgeladen. Nur Publikationsnachweis!
Autor*in
Schmidt, M.;
Rückert, UlrichUniBi
Abstract / Bemerkung
In this paper a novel approach for the storage and
access of an index used in internet search engines (Information
Retrieval) is presented. The index provides a mapping
from search terms to documents. The Binary Neural
Associative Memory (BiNAM) stores an index by associating
document signatures and document locations in a
distributed and content addressable way. The system presented
here has a high memory efficiency of more than
90%. The trade-off between memory consumption and
precision of the query-results is examined. A scalable system
architecture is presented. The architecture exploits
the parallel structure of the BiNAM. The association time
is estimated to be orders of magnitude faster than a software
solution. The system is realized as a modular PCI
architecture. The maximum capacity of the first version is
768MByte memory which allows to implement a BiNAM
of 80k neurons with 80k inputs each. In such a system
approximately 64 million associations can be stored and
accessed within 330ns per association.
Stichworte
software solution;
Internet;
scalable system architecture;
embedded neural associative memory;
mapping;
document locations;
content-based information retrieval;
BiNAM;
Internet search engines;
content-addressable storage;
content-based retrieval;
search engines;
information retrieval;
document signatures;
memory consumption;
modular PCI architecture
Erscheinungsjahr
2001
Titel des Konferenzbandes
Parallel and Distributed Processing, 2001. Proceedings. Ninth Euromicro Workshop on
Seite(n)
443-450
ISBN
0769509878
Page URI
https://pub.uni-bielefeld.de/record/2285870
Zitieren
Schmidt M, Rückert U. Content-based information retrieval using an embedded neural associative memory. In: Parallel and Distributed Processing, 2001. Proceedings. Ninth Euromicro Workshop on. IEEE Comput. Soc; 2001: 443-450.
Schmidt, M., & Rückert, U. (2001). Content-based information retrieval using an embedded neural associative memory. Parallel and Distributed Processing, 2001. Proceedings. Ninth Euromicro Workshop on, 443-450. IEEE Comput. Soc. https://doi.org/10.1109/EMPDP.2001.905073
Schmidt, M., and Rückert, Ulrich. 2001. “Content-based information retrieval using an embedded neural associative memory”. In Parallel and Distributed Processing, 2001. Proceedings. Ninth Euromicro Workshop on, 443-450. IEEE Comput. Soc.
Schmidt, M., and Rückert, U. (2001). “Content-based information retrieval using an embedded neural associative memory” in Parallel and Distributed Processing, 2001. Proceedings. Ninth Euromicro Workshop on (IEEE Comput. Soc), 443-450.
Schmidt, M., & Rückert, U., 2001. Content-based information retrieval using an embedded neural associative memory. In Parallel and Distributed Processing, 2001. Proceedings. Ninth Euromicro Workshop on. IEEE Comput. Soc, pp. 443-450.
M. Schmidt and U. Rückert, “Content-based information retrieval using an embedded neural associative memory”, Parallel and Distributed Processing, 2001. Proceedings. Ninth Euromicro Workshop on, IEEE Comput. Soc, 2001, pp.443-450.
Schmidt, M., Rückert, U.: Content-based information retrieval using an embedded neural associative memory. Parallel and Distributed Processing, 2001. Proceedings. Ninth Euromicro Workshop on. p. 443-450. IEEE Comput. Soc (2001).
Schmidt, M., and Rückert, Ulrich. “Content-based information retrieval using an embedded neural associative memory”. Parallel and Distributed Processing, 2001. Proceedings. Ninth Euromicro Workshop on. IEEE Comput. Soc, 2001. 443-450.
Google Scholar
ISBN Suche