Bidirectional Associative Memories

Bidirectional Associative Memories (BAM) based on Kosko's model are implemented through iterative algorithms and present stability problems. Also, these models along with other models based on different methods, have not been able to perfectly recall all trained patterns. In this paper we present an English-Spanish / Spanish-English translator based on a new BAM model denominated Alpha-Beta BAM, whose process is non iterative and does not require to find stable states. The translator recalls the whole set of learned patterns, even when the presented word is incomplete.

Bidirectional Associative Memories (BAM) based on Kosko's model are implemented through iterative algorithms and present stability problems. Also, these models along with other models based on different methods, have not been able to perfectly recall all trained patterns. In this paper we present an English-Spanish / Spanish-English translator based on a new BAM model denominated Alpha-Beta BAM, whose process is non iterative and does not require to find stable states. The translator recalls the whole set of learned patterns, even when the presented word is incomplete.

Associative memory is one of the primary functions of the human brain. In the literature, there are several neural networks based models that represent associative memory with the help of pattern associations. In this paper, we model the associative memory activity using Formal Concept Analysis (FCA), which is a standard technique for data and knowledge processing. In our proposal, patterns are associated with the help of object-attribute relations and the memory is represented using the formal concepts generated using FCA. We show that the extent and intent relations in the concepts help us to recall the patterns bi-directionally. Further, we model the pattern recall process for the given input even when the exact match is not found in the memory, using the concept hierarchies in the concept lattice.

Bidirectional Associative Memories (BAM) based on Kosko's model are implemented through iterative algorithms and present stability problems. Also, these models along with other models based on different methods, have not been able to perfectly recall all trained patterns. In this paper we present an English-Spanish / Spanish-English translator based on a new BAM model denominated Alpha-Beta BAM, whose process is non iterative and does not require to find stable states. The translator recalls the whole set of learned patterns, even when the presented word is incomplete.

In this work a new Bidirectional Associative Memory model, surpassing every other past and current model, is presented. This new model is based on Alpha–Beta associative memories, from whom it inherits its name. The main and most important characteristic of Alpha–Beta bidirectional associative memories is that they exhibit perfect recall of all patterns in the fundamental set, without requiring the fulfillment of any condition. The capacity they show is 2min(n,m), being n and m the input and output patterns dimensions, respectively. Design and functioning of this model are mathematically founded, thus demonstrating that pattern recall is always perfect, with no regard to the trained pattern characteristics, such as linear independency, orthogonality, or Hamming distance. Two applications illustrating the optimal functioning of the model are shown: a translator and a fingerprint identifier.