A spiking neural architecture that learns tasks

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Citation (Scopus)

Abstract

Cognitive architectures based on neural networks typically use the Basal Ganglia to model sequential behavior. A challenge for such models is to explain how the Basal Ganglia can learn to do new tasks relatively quickly. Here we present a model in which task-specific procedural knowledge is stored in a separate memory, and is executed by general procedures in the Basal Ganglia. In other words, learning happens elsewhere. The implementation discussed here is implemented in the Nengo cognitive architecture, but based on the principles of the PRIMs architecture. As a demonstration we model data from a mind-wandering experiment.
Original languageEnglish
Title of host publicationProceedings of ICCM 2019 - 17th International Conference on Cognitive Modeling
EditorsTerrence C. Stewart
PublisherApplied Cognitive Science Lab, Penn State
Pages253-258
Number of pages6
ISBN (Print)9780998508238
Publication statusPublished - 2020
Event17th International Conference on Cognitive Modeling (2020) - Barcelona, Spain
Duration: 17-Aug-202018-Aug-2020

Publication series

NameProceedings of ICCM 2019 - 17th International Conference on Cognitive Modeling

Conference

Conference17th International Conference on Cognitive Modeling (2020)
Country/TerritorySpain
CityBarcelona
Period17/08/202018/08/2020

Keywords

  • Basal Ganglia
  • Mind Wandering
  • Nengo
  • PRIMS
  • Skill Acquisition
  • Spiking neural networks

Fingerprint

Dive into the research topics of 'A spiking neural architecture that learns tasks'. Together they form a unique fingerprint.

Cite this