Autoassociative memory

From Wikipedia, the free encyclopedia
Jump to: navigation, search

Autoassociative memory, also known as auto-association memory or an autoassociation network, is a generic term that refers to all types of memories that enable 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[citation needed].


Traditional memory[edit]

Traditional memory[clarification needed] stores data at a unique address and can recall the data upon presentation of the complete unique address.

Autoassociative memory[edit]

Autoassociative memories are capable of retrieving a piece of data upon presentation of only partial information[clarification needed] from that piece of data.


For example, the sentence fragments presented below are sufficient for most humans to recall the missing information.

  1. "To be or not to be, that is _____."
  2. "I came, I saw, _____."

Most readers will realize the missing information is in fact:

  1. "To be or not to be, that is the question."
  2. "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[edit]

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[edit]

Bidirectional Associative Memories (BAM)[3] are artificial neural networks that have long been used for performing heteroassociative recall.


External links[edit]