Title :
Storage capacity of bidirectional associative memories
Author :
Wang, B.H. ; Vachtsevanos, G.
Author_Institution :
Sch. of Electr. Eng., Georgia Inst. of Technol., Atlanta, GA, USA
Abstract :
The authors derive the storage capacity of a discrete bidirectional associative memory (BAM) based on the correct learning condition. The correct learning condition is a relaxed sufficient condition for a BAM matrix to possess the perfect recall property. In fact, the perfect recall property depends only on the way the equilibrium points are formed, since a discrete BAM is always asymptotically stable. The storage capacity provides a measure of probability that a given input to the BAM is perfectly recalled under the given situation. A comparison study between analytical and experimental results is reported. This experimental verification demonstrates the accuracy of the analytically derived formula for storage capacity
Keywords :
content-addressable storage; neural nets; BAM matrix; asymptotically stable; auto-associative BAM; bidirectional associative memories; correct learning condition; discrete BAM; equilibrium points; perfect recall; relaxed sufficient condition; storage capacity; Associative memory; Asymptotic stability; Capacity planning; Differential equations; Encoding; Lyapunov method; Magnesium compounds; Neural networks; Pattern analysis; Sufficient conditions;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170636