Associative memory using temporal relations

As an alternative to the digital approach for implementing an associative memory the authors present a mixed digital analog approach based on a biological model. They propose to develop the theory for an associative memory and data reconstruction system based on the biological function of the cortex. There are two motivations for this research. First, the analog and parallel nature of the neural network approach may provide an efficient technique to achieve the high speed requirement for real-time coding systems with less hardware than both digital techniques and adaptive neural techniques. Second, the biological neural network may be useful as a model of the coding functions of the human brain. The proposed circuit realizing such a theory is much faster, extremely small in area, and more efficient than current systems. The complete associative memory circuit together with its simulation results are presented