Skip to main navigation Skip to search Skip to main content

Diffusion of neuromodulators for temporal credit assignment

  • Joao Barretto-Bittar*
  • , Anna Levina
  • , Emmanouil Giannakakis
  • , Roxana Zeraati*
  • *Corresponding author for this work

Research output: Contribution to journal › Short survey › peer-review

Abstract

Biological learning achieves temporal credit assignment despite sparse and imprecise feedback, often relying on neuromodulatory signals acting over space and time. Here, we introduce a learning mechanism in which error information diffuses locally through the network, similar to volume transmission of neuromodulators. This distributed modulation allows neurons to learn even in the absence of direct feedback, using the local concentration of the diffusing credit signal. Applied to recurrent spiking neural networks with sparse feedback connectivity, diffusive credit signaling improves learning across three benchmark tasks. Using eligibility propagation as a baseline, we show how diffusion-based modulation can provide a plausible mechanism for credit assignment in sparsely connected neural circuits.
Original languageEnglish
Article numbere2608831123
Number of pages3
JournalProceedings of the National Academy of Sciences of the United States of America
Volume123
Issue number38
DOIs
Publication statusPublished - 22 Sept 2026

Keywords

  • temporal credit assignment
  • neuromodulators
  • RNN

Fingerprint

Dive into the research topics of 'Diffusion of neuromodulators for temporal credit assignment'. Together they form a unique fingerprint.

Cite this