Fading intelligence theory: A theory on keeping artificial intelligence safety for the future

摘要

As a result of unstoppable rise of Artificial Intelligence, there has been a remarkable focus on the question of “Will intelligent systems be safe for humankind of the future?” Because of that, many researchers have started to direct their works on dealing with problems that may cause problems on enabling Artificial Intelligence systems to behave out of control or take positions dangerous for humans. Such research works are currently included under the literature of Artificial Intelligence Safety and / or Future of Artificial Intelligence. In the context of the explanations, this research paper proposes a theory on achieving safe intelligent systems by considering life-time of an Artificial Intelligence based system according to some operational variables and eliminate - terminate an intelligent system, which is `old enough' to operate for giving chance to new generations of systems, which seem safer. The paper makes a brief introduction to the theory and opens doors widely for further research on it.