Title | ||
---|---|---|
Storage and recall capabilities of fuzzy morphological associative memories with adjunction-based learning |
Abstract | ||
---|---|---|
We recently employed concepts of mathematical morphology to introduce fuzzy morphological associative memories (FMAMs), a broad class of fuzzy associative memories (FAMs). We observed that many well-known FAM models can be classified as belonging to the class of FMAMs. Moreover, we developed a general learning strategy for FMAMs using the concept of adjunction of mathematical morphology. In this paper, we describe the properties of FMAMs with adjunction-based learning. In particular, we characterize the recall phase of these models. Furthermore, we prove several theorems concerning the storage capacity, noise tolerance, fixed points, and convergence of auto-associative FMAMs. These theorems are corroborated by experimental results concerning the reconstruction of noisy images. Finally, we successfully employ FMAMs with adjunction-based learning in order to implement fuzzy rule-based systems in an application to a time-series prediction problem in industry. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1016/j.neunet.2010.08.013 | Neural Networks |
Keywords | Field | DocType |
error correction,mathematical morphology,associative memory,time series prediction,fixed point | Content-addressable memory,Associative property,Mathematical morphology,Fuzzy logic,Artificial intelligence,Artificial neural network,Rule of inference,Adjunction,Machine learning,Mathematics,Fuzzy rule | Journal |
Volume | Issue | ISSN |
24 | 1 | 0893-6080 |
Citations | PageRank | References |
24 | 0.64 | 46 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Marcos Eduardo Valle | 1 | 226 | 17.84 |
Peter Sussner | 2 | 880 | 59.25 |