Transforming task representations to perform novel tasks.

ABSTRACT: An important aspect of intelligence is the ability to adapt to a novel task without any direct experience (zero shot), based on its relationship to previous tasks. Humans can exhibit this cognitive flexibility. By contrast, models that achieve superhuman performance in specific tasks often fail to adapt to even slight task alterations. To address this, we propose a general computational framework for adapting to novel tasks based on their relationship to prior tasks. We begin by learning vector representations of tasks. To adapt to new tasks, we propose metamappings, higher-order tasks that transform basic task representations. We demonstrate the effectiveness of this framework across a wide variety of tasks and computational paradigms, ranging from regression to image classification and r

SUBMITTER: Lampinen AK 

PROVIDER: S-EPMC7777120 | biostudies-literature | 2020 Dec

REPOSITORIES: biostudies-literature