Article

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

2021-10-21

Abstract excerpt

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...

Topics

Open a Topic to create a Post that cites this publication.

Uncategorized literature

Identifiers and source

Literature Corpus work: fe35ce61-2115-5b5e-93eb-b75b31dd31c6
DOI: 10.1101/2021.10.20.465187

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Abstract representations emerge naturally in neural networks trained to perform multiple tasksDOI 10.1101/2021.10.20.465187Read

Abstract representations emerge in human hippocampal neurons during inference behaviorSemantic proximity Read

Neural representations supporting generalization under continual learningSemantic proximity Read

Leveraging prior concept learning improves ability to generalize from few examples in computational models of human object recognitionSemantic proximity Read

Hierarchical Emergence Profiles of Human-Derived Dimensions are a Fundamental Property of Deep Neural NetworksSemantic proximity Read

Learning generalizable representations through efficient codingSemantic proximity Read

Learning generalizable representations through efficient codingSemantic proximity Read

Learning generalizable representations through efficient codingSemantic proximity Read

Generalization in Sensorimotor Networks Configured with Natural Language InstructionsSemantic proximity Read

Generalizing Functions in Sparse DomainsSemantic proximity Read

Online abstraction during statistical learning revealed by neural entrainment from intracranial recordingsSemantic proximity Read

Computational reconstruction of mental representations using human behaviorSemantic proximity Read

Neural Taskonomy: Inferring the Similarity of Task-Derived Representations from Brain ActivitySemantic proximity Read