Article

Flexible multitask computation in recurrent networks utilizes shared dynamical motifs

2022-08-15

Abstract excerpt

Flexible computation is a hallmark of intelligent behavior. Yet, little is known about how neural networks contextually reconfigure for different computations. Humans are able to perform a new task without extensive training, presumably through the composition of elementary processes that were previously learned. Cognitive scientists have long hypothesized the possibility of a compositional neural code, where comp...

Topics

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

Identifiers and source

Literature Corpus work: 87f3c72a-8438-55d4-b2d4-82d47daffbcb
DOI: 10.1101/2022.08.15.503870

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Flexible multitask computation in recurrent networks utilizes shared dynamical motifsDOI 10.1101/2022.08.15.503870Read

Multitasking Recurrent Networks Utilize Compositional Strategies for Control of MovementSemantic proximity Read

Common features in plastic changes rather than constructed structures in recurrent neural network prefrontal cortex modelsSemantic proximity Read

Compositional Recombination Relies on a Distributed Cortico-Cerebellar NetworkSemantic proximity Read

Compositional Recombination Relies on a Distributed Cortico-Cerebellar NetworkSemantic proximity Read

Learning sculpts orthogonal task manifolds for continual skill learning in recurrent networksSemantic proximity Read

Nonlinear manifolds underlie neural population activity during behaviourSemantic proximity Read

Spatiotemporal discrimination in attractor networks with short-term synaptic plasticitySemantic proximity Read

Geometry of neural computation unifies working memory and planningSemantic proximity Read

Sparse mixed codes on shared manifolds for human-like spatial attention in artificial neural networksSemantic proximity Read

Network geometry shapes multi-task representational transformations across human cortexSemantic proximity Read

Learning complex temporal dependencies via local synaptic plasticitySemantic proximity Read

A neural mechanism for online discovery of latent contextsSemantic proximity Read