Autoassociative memory
Encyclopedia
Autoassociative memory, also known as auto-association memory or an autoassociation network, is often misunderstood to be only a form of backpropagation
or other neural networks. It is actually a more generic term that refers to all memories that enable one to retrieve a piece of data from only a tiny sample of itself.
Traditional memory stores data at a unique address and can recall the data upon presentation of the complete unique address. Autoassociative memories are capable of retrieving a piece of data upon presentation of only partial information from that piece of data. 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 have been shown to act as autoassociative memory since they are capable of remembering data by observing a portion of that data. Biological neural networks, on the other hand, are heteroassociative memories since they can remember a completely different item to the one presented as input. Bidirectional Associative Memories
(BAM) are Artificial Neural Networks that have long been used for performing heteroassociative recall.
For example, the fragments presented below should be all that's necessary to retrieve the appropriate memory:
The first example will make the reader fill in the blank with the word "infamy", while making him or her think of Franklin D. Roosevelt
. The second example is only a tiny phrase from William Shakespeare
's Hamlet
, yet readers will be able to associate it with the play. And finally, most people will be quick to translate Caesar
's quote over to "Veni, Vidi, Vici
". The conclusion to be drawn is that Autoassociation networks can recreate the whole from merely its small parts.
Backpropagation
Backpropagation is a common method of teaching artificial neural networks how to perform a given task. Arthur E. Bryson and Yu-Chi Ho described it as a multi-stage dynamic system optimization method in 1969 . It wasn't until 1974 and later, when applied in the context of neural networks and...
or other neural networks. It is actually a more generic term that refers to all memories that enable one to retrieve a piece of data from only a tiny sample of itself.
Traditional memory stores data at a unique address and can recall the data upon presentation of the complete unique address. Autoassociative memories are capable of retrieving a piece of data upon presentation of only partial information from that piece of data. 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 have been shown to act as autoassociative memory since they are capable of remembering data by observing a portion of that data. Biological neural networks, on the other hand, are heteroassociative memories since they can remember a completely different item to the one presented as input. Bidirectional Associative Memories
Bidirectional Associative Memory
Bidirectional associative memory 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...
(BAM) are Artificial Neural Networks that have long been used for performing heteroassociative recall.
For example, the fragments presented below should be all that's necessary to retrieve the appropriate memory:
- "A day that will live in ______"
- "To be or not to be"
- "I came, I saw, I conquered"
The first example will make the reader fill in the blank with the word "infamy", while making him or her think of Franklin D. Roosevelt
Franklin D. Roosevelt
Franklin Delano Roosevelt , also known by his initials, FDR, was the 32nd President of the United States and a central figure in world events during the mid-20th century, leading the United States during a time of worldwide economic crisis and world war...
. The second example is only a tiny phrase from William Shakespeare
William Shakespeare
William Shakespeare was an English poet and playwright, widely regarded as the greatest writer in the English language and the world's pre-eminent dramatist. He is often called England's national poet and the "Bard of Avon"...
's Hamlet
Hamlet
The Tragical History of Hamlet, Prince of Denmark, or more simply Hamlet, is a tragedy by William Shakespeare, believed to have been written between 1599 and 1601...
, yet readers will be able to associate it with the play. And finally, most people will be quick to translate Caesar
Julius Caesar
Gaius Julius Caesar was a Roman general and statesman and a distinguished writer of Latin prose. He played a critical role in the gradual transformation of the Roman Republic into the Roman Empire....
's quote over to "Veni, Vidi, Vici
Veni, vidi, vici
"Veni, vidi, vici" is a Latin sentence reportedly written by Julius Caesar in 47 BC as a comment on his short war with Pharnaces II of Pontus in the city of Zela ....
". The conclusion to be drawn is that Autoassociation networks can recreate the whole from merely its small parts.