<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Associative memories based on lattice algebra are of great interest in pattern recognition applications due to their excellent storage and recall properties. In this paper, a class of binary associative memory derived from lattice memories is presented, which is based on the definition of new complemented binary operations and threshold unary operations. The new learning method generates memories <bold>M</bold> and <bold>W</bold>; the former is robust to additive noise and the latter is robust to subtractive noise. In the recall step, the memories converge in a single step and use the same operation as the learning method. The storage capacity is unlimited, and in autoassociative mode there is perfect recall for the training set. Simulation results suggest that the proposed memories have better performance compared to other models.</p>
</abstract>

Associative memories based on lattice algebra are of great interest in pattern recognition applications due to their excellent storage and recall properties. In this paper, a class of binary associative memory derived from lattice memories is presented, which is based on the definition of new complemented binary operations and threshold unary operations. The new learning method generates memories M and W; the former is robust to additive noise and the latter is robust to subtractive noise. In the recall step, the memories converge in a single step and use the same operation as the learning method. The storage capacity is unlimited, and in autoassociative mode there is perfect recall for the training set. Simulation results suggest that the proposed memories have better performance compared to other models.

Binary Associative Memories with Complemented Operations

International Journal of Applied Mathematics and Computer Science

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

{"article-title":"Binary Associative Memories with Complemented Operations"}

Associative memories based on lattice algebra are of great interest in pattern recognition applications due to their excellent storage and recall properties....

Binary Associative Memories with Complemented Operations

Online veröffentlicht: 23. Juni 2023

Seitenbereich: 249 - 265

Eingereicht: 01. Aug. 2022

Akzeptiert: 27. Feb. 2023

DOI: https://doi.org/10.34768/amcs-2023-0019

Schlüsselwörter
associative memory, neural network, morphological associative memory, perfect recall

© 2023 Arturo Gamino-Carranza, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Binary Associative Memories with Complemented Operations

Online veröffentlicht: 23. Juni 2023

Seitenbereich: 249 - 265

Eingereicht: 01. Aug. 2022

Akzeptiert: 27. Feb. 2023

DOI: https://doi.org/10.34768/amcs-2023-0019

Schlüsselwörterassociative memory, neural network, morphological associative memory, perfect recall

© 2023 Arturo Gamino-Carranza, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Schlüsselwörter
associative memory, neural network, morphological associative memory, perfect recall