| Full text | |
| Author(s): |
Valle, Marcos Eduardo
[1]
Total Authors: 1
|
| Affiliation: | [1] Univ Estadual Campinas, Dept Appl Math, BR-13083859 Campinas, SP - Brazil
Total Affiliations: 1
|
| Document type: | Journal article |
| Source: | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS; v. 25, n. 7, p. 1372-1377, JUL 2014. |
| Web of Science Citations: | 10 |
| Abstract | |
An autoassociative memory (AM) that projects an input pattern onto a linear subspace is referred to as a subspace projection AM (SPAM). The optimal linear AM (OLAM), which can be used for the storage and recall of real-valued patterns, is an example of SPAM. In this brief we introduce a novel SPAM model based on the robust M-estimation method. In contrast to the OLAM and many other associative memory models, the robust SPAM represents a neural network in which the synaptic weights are iteratively adjusted during the retrieval phase. Computational experiments concerning the reconstruction of corrupted gray-scale images reveal that the novel memories exhibit an excellent tolerance with respect to salt and pepper noise as well as some tolerance with respect to Gaussian noise and blurred input images. (AU) | |
| FAPESP's process: | 13/12310-4 - Some generalizations of the recurrent correlation associative memories |
| Grantee: | Marcos Eduardo Ribeiro Do Valle Mesquita |
| Support Opportunities: | Regular Research Grants |