Fault tolerant hashing and information retrieval using back propagation

K Dontas; J Sarma; P Srinivasan; H Wechsler

doi:10.1109/HICSS.1990.205277

Back

Conference proceeding

Fault tolerant hashing and information retrieval using back propagation

K Dontas, J Sarma, P Srinivasan and H Wechsler

Twenty-Third Annual Hawaii International Conference on System Sciences, Vol.4, pp.345-352

Annual Hawaii International Conference on System Sciences, 23 (Kailua-Kona, Hawaii, USA, 01/02/1990–01/05/1990)

1990

DOI: 10.1109/HICSS.1990.205277

View Online

Abstract

The architecture and performance of neural networks designed and trained to compute hashing functions is described. The networks described are of the connectionist type and are capable of learning complex mappings using the back-propagation or error algorithm. Connectionist networks are robust, are capable of limited error correction, and offer several advantages over traditional hashing methods. Multiple indexing, which implements many-to-one mapping, can be easily realized by training a network for each key attribute. The neural network approach can be used to train a very large number of pattern associations by dividing a problem into smaller problems. This neural network consists of several subnetworks, each solving a specific mapping task. The experimental results show that small neural networks with simple processing elements can learn complex mapping that implement index search in constant time.

Information Retrieval

Information Technology

Fault tolerance

Design engineering

Databases

Neural networks

Fault tolerant systems

Error correction

Information systems

Indexing

Details

Title: Subtitle: Fault tolerant hashing and information retrieval using back propagation
Creators: K Dontas - Sch. of Inf. Technol. & Eng., George Mason Univ., Fairfax, VA, USA
J Sarma - Sch. of Inf. Technol. & Eng., George Mason Univ., Fairfax, VA, USA
P Srinivasan - University of Iowa, Computer Science
H Wechsler - Sch. of Inf. Technol. & Eng., George Mason Univ., Fairfax, VA, USA
Resource Type: Conference proceeding
Publication Details: Twenty-Third Annual Hawaii International Conference on System Sciences, Vol.4, pp.345-352
Conference: Annual Hawaii International Conference on System Sciences, 23 (Kailua-Kona, Hawaii, USA, 01/02/1990–01/05/1990)
DOI: 10.1109/HICSS.1990.205277
Publisher: IEEE Comput. Soc. Press
Language: English
Date published: 1990
Academic Unit: Nursing; Computer Science; Business Analytics
Record Identifier: 9984012897802771

Metrics

22 Record Views