Autoassociative memory

Autoassociative memory

Autoassociative memory, also known as auto-association memory or an autoassociation network, is a form of backpropagation or other neural networks that enables one to retrieve entire memories from only a tiny sample of itself. To draw a picture, 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. 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 " [http://en.wikiquote.org/wiki/Julius_Caesar Veni, Vidi, Vici] ". The conclusion to be drawn is that Autoassociation networks can recreate the whole from merely its small parts.

ee also

* Bidirectional Associative Memory

External links

* [http://www.heatonresearch.com/articles/2/page4.html Autoassociation]


Wikimedia Foundation. 2010.

Игры ⚽ Нужен реферат?

Look at other dictionaries:

  • Associative memory — may refer to: * a type of memory closely associated with neural networks; such as Bidirectional Associative Memory, Autoassociative memory and Hopfield net. * a type of computer memory; see Content addressable memory. * an aspect of human memory; …   Wikipedia

  • Bidirectional Associative Memory — usually referred to as BAM is a type of recurrent neural network. BAM was discovered by Kosko in 1988.Fact|date=October 2008 There are two types, auto and hetero. Topology It contains two layers of neurons that recursively send information… …   Wikipedia

  • Episodic memory — is the memory of unique personal experiences (events, times, places, associated emotions, and other conception based knowledge) that can be put in language. Semantic and episodic memory together make up the category of declarative memory, which… …   Wikipedia

  • Hopfield net — A Hopfield net is a form of recurrent artificial neural network invented by John Hopfield. Hopfield nets serve as content addressable memory systems with binary threshold units. They are guaranteed to converge to a local minimum, but convergence… …   Wikipedia

  • Neural Lab — Original author(s) Sergio Ledesma …   Wikipedia

  • Hopfield (RNA) — Una red de Hopfield es una forma de red neuronal artificial recurrente inventada por John Hopfield. Las redes de Hopfield se usan como sistemas de Memoria asociativa con unidades binarias. Están diseñadas para converger a un mínimo local, pero la …   Wikipedia Español

Share the article and excerpts

Direct link
Do a right-click on the link above
and select “Copy Link”