Unknown

Dataset Information

Abstract representations emerge naturally in neural networks trained to perform multiple tasks.


ABSTRACT: Humans and other animals demonstrate a remarkable ability to generalize knowledge across distinct contexts and objects during natural behavior. We posit that this ability to generalize arises from a specific representational geometry, that we call abstract and that is referred to as disentangled in machine learning. These abstract representations have been observed in recent neurophysiological studies. However, it is unknown how they emerge. Here, using feedforward neural networks, we demonstrate that the learning of multiple tasks causes abstract representations to emerge, using both supervised and reinforcement learning. We show that these abstract representations enable few-sample learning and reliable generalization on novel tasks. We conclude that abstract representations of sensory a

SUBMITTER: Johnston WJ 

PROVIDER: S-EPMC9950464 | biostudies-literature | 2023 Feb

REPOSITORIES: biostudies-literature