Title :
Characteristics of the Hopfield associative memory utilizing isomorphism relations
Author :
Lee, C.Y. ; Wang, J.S. ; Lee, R.C.T.
Author_Institution :
Inst. of Comput. Sci., Nat. Tsing Hua Univ., Hsinchu, Taiwan
fDate :
5/1/1994 12:00:00 AM
Abstract :
Isomorphism relations are utilized to analyze the Hopfield associative memory. When the number of fundamental memories m⩽3, it is proved that two Hopfield associative memories are isomorphic if they have the same mutual distances between the fundamental memories. The number of stable states and the synchronous convergence time of a Hopfield associative memory are shown to be less than or equal to 2 to the power 2m-1 and 4 to the power 2m-1, respectively, where m⩾1
Keywords :
Hopfield neural nets; content-addressable storage; Hopfield associative memory; fundamental memories; isomorphism relations; synchronous convergence time; Artificial intelligence; Associative memory; Computer science; Convergence; Hopfield neural networks; Hydrogen; Hypercubes; Neural networks; State-space methods; Upper bound;
Journal_Title :
Neural Networks, IEEE Transactions on
