Henning Sprekeler (Science of Intelligence), “Architectural Design Principles for Intelligence: Modularity vs. Integration”

Abstract:

The world is modular. So – intuitively – it seems clear that cognitive systems that deal with the world should benefit from a modular architecture. Simple or less important problems should use less cognitive resources than complex or important problems, which – intuitively – may be achieved by changing the degree of modularity that a system uses. More modular, less power consumption, shallower processing; more integrated, more power consumption, deeper processing. Is this indeed the case? Is it beneficial for a cognitive system to regulate its degree of modularity depending on task demand? Does the human brain do this? How can a system determine which degree of modularity to use? In this talk, we will first provide an update on the project, and then invite everyone for discussion.

The Zoom Link will be sent the day before the lecture.