Attention Capabilities for AI Systems

Much of present AI research is based on the assumption of computational systems with infinite resources, an assumption that is either explicitly stated or implicit in the work as researchers ignore the fact that most real-world tasks must be finished within certain time limits, and it is the role of intelligence to effectively deal with such limitations. Expecting AI systems to give equal treatment to every piece of data they encounter is not appropriate in most real-world cases; available resources are likely to be insufficient for keeping up with available data in even moderately complex environments. Even if sufficient resources are available, they might possibly be put to better use than blindly applying them to every possible piece of data. Finding inspiration for more intelligent resource management schemes is not hard, we need to look no further than ourselves. This paper explores what human attention has to offer in terms of ideas and concepts for implementing intelligent resource management and how the resulting principles can be extended to levels beyond human attention. We also discuss some ideas for the principles behind attention mechanisms for artificial (general) intelligences.