Title :
An introduction to the max-plus projection autoassociative morphological memory and some of its variations
Author :
Valle, Marcos Eduardo
Author_Institution :
Dept. of Appl. Math., Univ. of Campinas, Campinas, Brazil
Abstract :
In this paper, we present a novel lattice-based memory model called max-plus projection autoassociative morphological memory (max-plus PAMM). The max-plus PAMM yields the largest max-plus combination of the stored patterns which is less than or equal to the input. Such as the original autoassociative morphological memories (AMMs), it is idempotent and it gives perfect recall of undistorted patterns. Furthermore, the max-plus PAMM is very robust to dilative noise and it has less spurious memories than its corresponding AMM. This paper also presents two variations of the max-plus PAMM. The first yields the max-plus combination that is the Chebyshev-best approximation of the input while the second uses a noise masking strategy.
Keywords :
Chebyshev approximation; content-addressable storage; Chebyshev-best approximation; lattice-based memory model; max-plus PAMM; max-plus combination; max-plus projection autoassociative morphological memory; noise masking strategy; spurious memories; undistorted patterns; Chebyshev approximation; Kernel; Lattices; Mathematical model; Memory management; Noise; Vectors;
Conference_Titel :
Fuzzy Systems (FUZZ-IEEE), 2014 IEEE International Conference on
Conference_Location :
Beijing
Print_ISBN :
978-1-4799-2073-0
DOI :
10.1109/FUZZ-IEEE.2014.6891609