N. Homma (Japan) and M.M. Gupta (Canada)
Neural networks, self-organization, long-term memory.
This paper demonstrates that a novel neural structure can be useful for formation of long-term memory. An essential core of the proposed model is a control signal for learning or memory formation, inspired by a possible physiological learning mechanism observed in cerebral cortices and hip pocampus. From a physiological point of view, the control signal can be generated by the limbic system according to cognitive results. Simulation results show that the model can possess some physiologically observed features of hu man memory systems.
Important Links:
Go Back
