Autoassociative memory
Autoassociative memory, also known as auto-association memory or an autoassociation network, is any type of memory that enables one to retrieve a piece of data from only a tiny sample of itself. It is often misunderstood to be only a form of backpropagation or other neural networks.
Background
Traditional memory
Traditional memory stores data at a unique address and can recall the data upon presentation of the complete unique address.
Autoassociative memory
Autoassociative memories are capable of retrieving a piece of data upon presentation of only partial information from that piece of data.
Examples
For example, the sentence fragments presented below are sufficient for most humans to recall the missing information.
- "To be or not to be, that is _____."
- "I came, I saw, _____."
Most readers will realize the missing information is in fact:
- "To be or not to be, that is the question."
- "I came, I saw, I conquered."
This demonstrates the capability of autoassociative networks to recall the whole by using some of its parts.
Heteroassociative memory
Heteroassociative memories, on the other hand, can recall an associated piece of datum from one category upon presentation of data from another category. Hopfield networks [1] have been shown [2] to act as autoassociative memory since they are capable of remembering data by observing a portion of that data.
Bidirectional associative memory
Bidirectional associative memories (BAM)[3] are artificial neural networks that have long been used for performing heteroassociative recall.
References
- ↑
- ↑ Artificial Intelligence Illuminated - Ben Coppin - Google Books. Books.google.co.uk. Retrieved on 2013-11-20.
- ↑ http://sipi.usc.edu/~kosko/BAM.pdf