Article

Darwinian dynamics over recurrent neural computations for combinatorial problem solving

2020-11-06

Abstract excerpt

Efficient search in enormous combinatorial spaces is an essential component of intelligence. Humans, for instance, are often found searching for optimal action sequences, linguistic structures and causal explanations. Is there any computational domain that provides good-enough and fast-enough solutions to such a diverse set of problems, yet can be robustly implemented over neural substrates? Based on previous acco...

Topics

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

Identifiers and source

Literature Corpus work: 508a0741-b148-58f8-8a41-e9d986ab1fdf
DOI: 10.1101/2020.11.06.372284

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Darwinian dynamics over recurrent neural computations for combinatorial problem solvingDOI 10.1101/2020.11.06.372284Read

A surprising link between cognitive maps, successor-relation based reinforcement learning, and BTSPSemantic proximity Read

Is neural Darwinism Darwinism?Semantic proximity Read

Beyond Deep Learning—Space, Time, and EmergenceSemantic proximity Read

Evolvable neuronal paths: a novel basis for information and search in the brain.Semantic proximity Read

Copying and evolution of neuronal topology.Semantic proximity Read

Dynamic Models of Neural Population DynamicsSemantic proximity Read

Computational neural mechanisms of goal-directed planning and problem solvingSemantic proximity Read

Computation noise promotes cognitive resilience to adverse conditions during decision-makingSemantic proximity Read

Learning to select computations in recurrent neural circuitsSemantic proximity Read

Emergence of algorithmic language in genetic systems.Semantic proximity Read

Learning generalizable representations through efficient codingSemantic proximity Read

Learning generalizable representations through efficient codingSemantic proximity Read