Title :
A dynamic thresholding approach to improve higher order associative memory capability
Author :
Huang, Yo-Ping ; Gustafson, Donald
Author_Institution :
Dept. of Electr. Eng., Texas Tech Univ., Lubbock, TX, USA
Abstract :
A dynamic thresholding method is presented to improve higher order sparsely encoded associative memory (SEAM) performance. Under such a scheme, the SEAM model is shown to have greater storage capacity than the ordinary associative memory. The results are also considered from the information point of view. Simulation results are consistent with the theoretical analysis
Keywords :
content-addressable storage; neural nets; SEAM model; dynamic thresholding; higher order; sparsely encoded associative memory; storage capacity; Approximation methods; Associative memory; Computational modeling; H infinity control; Interference; Neurons; Probes; Upper bound;
Conference_Titel :
Circuits and Systems, 1992., Proceedings of the 35th Midwest Symposium on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-0510-8
DOI :
10.1109/MWSCAS.1992.271231
