Pattern Recognition, International Conference on (2000)
Sept. 3, 2000 to Sept. 8, 2000
Richard C. Wilson , University of York
Edwin R. Hancock , University of York
This paper addresses the problem of how to identify the optimal excitation function for the recurrent correlation associative memory. We present a model of pattern recovery, which allows us to measure probability of bit-error. By minimizing this measure, we are able to numerically locate the excitation function, which results in the minimum error of pattern recall. Additionally, we show that minimizing a simpler measure of pattern overlap leads to an analytical expression for the exciation function, which is exponential. We compare the performance of the numerical and exponential functions. This reveals that the more easily controlled exponential is only slightly poorer in its performance.
E. R. Hancock and R. C. Wilson, "Optimizing Pattern Recovery in Recurrent Correlation Associative Memories," Pattern Recognition, International Conference on(ICPR), Barcelona, Spain, 2000, pp. 6005.