Title :
Self indexing of neural memories
Author_Institution :
Dept. of Electr. & Comput. Eng., Louisiana State Univ., Baton Rouge, LA, USA
Abstract :
It is shown that the property of self-indexing allows stable memories to be generated by very short subsequences. This defines a mechanism for sequential associative memory and for the sequential generation of a number of states. By using generator sequences longer than the minimum length the mechanism can also correct errors
Keywords :
content-addressable storage; data compression; error correction; memory architecture; neural nets; error correction; self indexing of neural memories; sequential associative memory; short subsequences; stable memories; Associative memory; Biological system modeling; Data compression; Error correction; Indexing; Neural networks; Neurons; Physics; Random variables; Sequences;
Conference_Titel :
Circuits and Systems, 1990., IEEE International Symposium on
Conference_Location :
New Orleans, LA
DOI :
10.1109/ISCAS.1990.112292