Multitask computation through dynamics in recurrent spiking neural networks

In this work, inspired by cognitive neuroscience experiments, we propose recurrent spiking neural networks trained to perform multiple target tasks. These models are designed by considering neurocognitive activity as computational processes through dynamics. Trained by input–output examples, these s...

Full description

Saved in:
Bibliographic Details
Published inScientific reports Vol. 13; no. 1; pp. 3997 - 20
Main Authors Pugavko, Mechislav M., Maslennikov, Oleg V., Nekorkin, Vladimir I.
Format Journal Article
LanguageEnglish
Published London Nature Publishing Group UK 10.03.2023
Nature Publishing Group
Nature Portfolio
Subjects
639/766/530/2801
639/766/530/2803
Cognition
Cognitive ability
Firing pattern
Humanities and Social Sciences
Machine learning
multidisciplinary
Nervous system
Neural networks
Neurons
Neurosciences
Science
Science (multidisciplinary)
Online AccessGet full text

Cover

More Information
Summary:In this work, inspired by cognitive neuroscience experiments, we propose recurrent spiking neural networks trained to perform multiple target tasks. These models are designed by considering neurocognitive activity as computational processes through dynamics. Trained by input–output examples, these spiking neural networks are reverse engineered to find the dynamic mechanisms that are fundamental to their performance. We show that considering multitasking and spiking within one system provides insightful ideas on the principles of neural computation.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:2045-2322
2045-2322
DOI:10.1038/s41598-023-31110-z