Online

Powell, Nathaniel V.

Mathematics and Statistics

2016

MS

At the heart of statistical learning lies the concept of uncertainty. Similarly, embodied agents such as robots and animals must likewise address uncertainty, as sensation is always only a partial reflection of reality. This thesis addresses the role that uncertainty can play in a central building block of intelligence: categorization. Cognitive agents are able to perform tasks like categorical perception through physical interaction (active categorical perception; ACP), or passively at a distance (distal categorical perception; DCP). It is possible that the former scaffolds the learning of the latter. However, it is unclear whether DCP indeed scaffolds ACP in humans and animals, nor how a robot could be trained to likewise learn DCP from ACP. Here we demonstrate a method for doing so which involves uncertainty: robots perform ACP when uncertain and DCP when certain. Furthermore, we demonstrate that robots trained in such a manner are more competent at categorizing novel objects than robots trained to categorize in other ways. This suggests that such a mechanism would also be useful for humans and animals, suggesting that they may be employing some version of this mechanism.