Matching in memristor based auto-associative memory with application to pattern recognition

The study of memristor based associative memory design has become increasingly important with the advent of new hybrid CMOS Molecular (CMOL) technologies. To date, only a very few papers have been published on this topic. Specifically, little is know regarding partial or full match is possible in CMOL technologies which use CMOS and memristors. To this end, a new approach to implement partial of full matching in associative memory is introduced. The method is based on complementary transformations at the input. This method is augmented with transformations that specifically enhance partial or full matching of the input data while improving the performance. Experimental results show that the proposed methodology can achieve better performance than similar designs in the literature.