Title :
Fixed points of autoassociative morphological memories
Author_Institution :
Inst. of Math., Stat., & Sci. Comput., Univ. Estadual de Campinas, Sao Paulo, Brazil
Abstract :
We recently introduced a class of highly nonlinear associative memories called morphological associative memories. We have previously shown that autoassociative morphological memories (AMMs) exhibit many desirable characteristics, including optimal absolute storage capacity and one-step convergence (G.X. Ritter et al., 1998). Other aspects of AMM performance still require more detailed analysis and/or improvement. The paper provides considerable insight into the functionality of AMMs by giving necessary and sufficient conditions for fixed points. We then show that the output generated upon presentation of an input pattern x is either the smallest fixed point ⩾x or the largest fixed point ⩽x
Keywords :
content-addressable storage; mathematical morphology; minimax techniques; neural nets; AMM performance; autoassociative morphological memories; highly nonlinear associative memories; input pattern; largest fixed point; morphological associative memories; one-step convergence; optimal absolute storage capacity; smallest fixed point; sufficient conditions; Algebra; Artificial neural networks; Associative memory; Computer networks; Convergence; Lattices; Mathematics; Minimax techniques; Neural networks; Statistics;
Conference_Titel :
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location :
Como
Print_ISBN :
0-7695-0619-4
DOI :
10.1109/IJCNN.2000.861536
