A conceptual associative memory with full memory capacity and ability to associate arbitrary patterns

In this paper, a conceptual associative memory (CAM), which uses the conceptual layer(s) to associate input/output layers, is proposed to achieve the most important requirement for neural networks as memory devices, that is, the ability to store arbitrary patterns in networks and retrieve them correctly. The CAM has many advantages, such as the able to associate arbitrary patterns like the BP networks (Back Propagation networks), full memory capacity like the ART1 (Adaptive Resonance Theory 1) networks, fast construction of weights, easy update of the memory system, and capable of handling both spatial and temporal patterns. These features make the CAM very attractive as the building block of memory systems. Therefore, it is possible to build databases or expert systems based on CAM