Bidirectional Associative Memory usually referred to as 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 hetro-associative. BAM is hetro-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.
| Property | Value |
|---|
| dbpprop:abstract
|
- Bidirectional Associative Memory usually referred to as 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 hetro-associative. BAM is hetro-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.
|
| dbpprop:reference
| |
| rdfs:comment
|
- Bidirectional Associative Memory usually referred to as 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 hetro-associative. BAM is hetro-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.
|
| rdfs:label
|
- Bidirectional Associative Memory
|
| owl:sameAs
| |
| skos:subject
| |
| foaf:page
| |
| is dbpprop:redirect
of | |
![[RDF Data]](/statics/sw-cube.png)
