Bidirectional associative memory
≈ 3 min read
Names in other languages
No names in other languages are held for this entry yet.
Article bodies are English and are not machine-translated. A name in another language is not a translation of the article.
Bidirectional associative memory (BAM) is a type of recurrent neural network. BAM was introduced by Bart Kosko in 1988. There are two types of associative memory, auto-associative and hetero-associative.
BAM is hetero-associative, meaning given a pattern it can return another pattern which is potentially of a different size. It is similar to the Hopfield network in that they are both forms of associative memory. However, Hopfield nets return patterns of the same size.
It is said to be bi-directional as it can respond to inputs from either the input or the output layer.
Bidirectional associative memory (BAM) is a type of recurrent neural network. BAM was introduced by Bart Kosko in 1988. There are two types of associative memory, auto-associative and hetero-associative.
BAM is hetero-associative, meaning given a pattern it can return another pattern which is potentially of a different size. It is similar to the Hopfield network in that they are both forms of associative memory. However, Hopfield nets return patterns of the same size.
It is said to be bi-directional as it can respond to inputs from either the input or the output layer.
Learning
Imagine we wish to store two associations, A1:B1 and A2:B2. A1 = (1, 0, 1, 0, 1, 0), B1 = (1, 1, 0, 0) A2 = (1, 1, 1, 0, 0, 0), B2 = (1, 0, 1, 0) These are then transformed into the bipolar forms: X1 = (1, -1, 1, -1, 1, -1), Y1 = (1, 1, -1, -1) X2 = (1, 1, 1, -1, -1, -1), Y2 = (1, -1, 1, -1) From there, we calculate M = \sum{\! X_i^T Y_i} where X_i^T denotes the transpose.
So, M = \left[ {\begin{array}{*{10}c} 2 & 0 & 0 & -2 \\ 0 & -2 & 2 & 0 \\ 2 & 0 & 0 & -2 \\ -2 & 0 & 0 & 2 \\ 0 & 2 & -2 & 0 \\ -2 & 0 & 0 & 2 \\ \end{array} } \right]
Recall
To retrieve the association A1, we multiply it by M to get (4, 2, -2, -4), which, when run through a threshold, yields (1, 1, 0, 0), which is B1. To find the reverse association, multiply this by the transpose of M.
Capacity
The memory or storage capacity of BAM may be given as \min(m,n) , where " n " is the number of units in the X layer and " m " is the number of units in the Y layer. The internal matrix has n x p independent degrees of freedom, where n is the dimension of the first vector (6 in this example) and p is the dimension of the second vector (4).
This allows the BAM to be able to reliably store and recall a total of up to min(n,p) independent vector pairs, or min(6,4) = 4 in this example. The capacity can be increased above by sacrificing reliability (incorrect bits on the output).
The Energy Function proposed by Kosko is E(A,B) = -AMB^T for the bidirectional case, which for a particular case A=B corresponds to Hopfield's auto-associative energy function. (i.e. E(A,B) = -AMA^T ).
See also
Autoassociative memory Self-organizing feature map
References
Bidirectional associative memories – ACM Portal Reference
Text derived from https://en.wikipedia.org/w/index.php?oldid=1250280942 under CC BY-SA 4.0; modifications have been made.