Developing a reliable learning model for cognitive classification tasks using an associative memory

An associative memory based learning model is proposed which uses a short and long-term memory and a ranking mechanism to manage the transition of reference vectors between two memories. The memorizing process is similar to that in human memory. In addition, an optimization algorithm is used to adjust the reference vectors components as well as their distribution, continuously. Comparing to other learning models like neural networks, the main advantage of the proposed model is no need to pre-training phase as well as its hardware-friendly structure which makes it implementable by an efficient LSI architecture without requiring a large amount of resources. The system was implemented on an FPGA platform and tested with real data of handwritten and printed English characters and the classification results found satisfactory.