We propose the distributed associative memory (DAM) model as a paradigm for fault-tolerant information retrieval and database organization. The fault tolerance is with respect to noise (errors) in the input key and/or corruption in the memory itself. Our approach is based on the DAM model originally introduced by Kohonen for image recognition. Essentially, DAM is a memory matrix which can modify the flow of information. Stimulus vectors are associated with response vectors and the result of this association is spread over the entire memory space. Because the information is distributed in memory, the overall function of memory becomes resistant to faults in memory and degraded (noisy) stimulus vectors. In order to verify our approach experimentally, we created a database of names taken from a student directory. We performed numerous experiments to evaluate fault tolerance of database retrieval. Finally, we developed a fault-tolerant relational database using the DAM paradigm.
|Original language||English (US)|
|Number of pages||1|
|Issue number||1 SUPPL|
|State||Published - Jan 1 1988|
|Event||International Neural Network Society 1988 First Annual Meeting - Boston, MA, USA|
Duration: Sep 6 1988 → Sep 10 1988