The concept of time varying associative memory is introduced. It is
briefly described how such a memory is potentially motivated by the mechanism
in biological systems. A Generalized Convergence Theorem is described. One concrete procedure to synthesize such an associative memory is described. Another approach for arriving at a time varying associative memory is briefly described. Important generalizations of associative memory are briefly described.
Living systems/machines such as homosapiens, lions, tigers etc have the ability to associate externally presented one/two/three dimensional information such as audio signal/images/three dimensional scenes with the information stored in the brain. This highly accurate ability of association of information is amazingly achieved through the bio-chemical circuitry in the brain. Starting in 1950’s researchers tried arriving at modeling the neuronal circuitry. Thus the research field of artificial neural networks took birth. The so called, perceptron was shown to be able to classify linear separable patterns. Since the Ex-clusive OR gate cannot be synthesized through any perceptron (as the gate outputs are not linearly separable), the interest in artificial neural networks faded away. In the 1970’s , it was shown that multi-layer feed forward neural network such as a multi-layer perceptron is able to classify non-linearly separable patterns.
In 1980’s Hopfield revived the interest in the area of artificial neural networks through a model of associative memory. His model of associative memory is described in detail in section 2. The main contribution is a convergence theorem which shows that the artifical neural network reaches a
memory/stable state starting in any arbitrary initial input (in a certain important mode of operation). He also demonstrated several interesting variations of associative memory.

Article Source: http://www.articleset.com